Merge pull request #3253 from pipecat-ai/changelog-0.0.98

Release 0.0.98 - Changelog Update

.github/workflows/generate-changelog.yml

@@ -0,0 +1,174 @@
+name: Generate Changelog for Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Release version (e.g., 0.0.97)"
+        required: true
+        type: string
+      date:
+        description: "Release date (YYYY-MM-DD format, defaults to today)"
+        required: false
+        type: string
+        default: ""
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  generate-changelog:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev
+
+      - name: Set release date
+        id: set_date
+        run: |
+          if [ -z "${{ inputs.date }}" ]; then
+            RELEASE_DATE=$(date +%Y-%m-%d)
+            echo "Using today's date: $RELEASE_DATE"
+          else
+            RELEASE_DATE="${{ inputs.date }}"
+            echo "Using provided date: $RELEASE_DATE"
+          fi
+          echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
+
+      - name: Validate inputs
+        run: |
+          # Validate version format (basic check)
+          if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
+            echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
+            exit 1
+          fi
+
+          # Validate date format if provided
+          if [ -n "${{ inputs.date }}" ]; then
+            if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
+              # Try macOS date format
+              if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
+                echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
+                exit 1
+              fi
+            fi
+          fi
+
+      - name: Check for changelog fragments
+        id: check_fragments
+        run: |
+          FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
+          echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
+
+          if [ "$FRAGMENT_COUNT" -eq "0" ]; then
+            echo "❌ Error: No changelog fragments found in changelog/"
+            echo ""
+            echo "Cannot create a release without changelog entries."
+            echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
+            exit 1
+          fi
+
+          # Validate fragment types
+          VALID_TYPES="added changed deprecated removed fixed security"
+          INVALID_FRAGMENTS=""
+
+          for file in changelog/*.md; do
+            # Skip template
+            if [[ "$file" == "changelog/_template.md.j2" ]]; then
+              continue
+            fi
+            
+            # Extract type from filename (e.g., 1234.added.md -> added)
+            filename=$(basename "$file")
+            # Handle both 1234.added.md and 1234.added.2.md patterns
+            type=$(echo "$filename" | sed -E 's/^[0-9]+\.([a-z]+)(\.[0-9]+)?\.md$/\1/')
+            
+            # Check if type is valid
+            if ! echo "$VALID_TYPES" | grep -wq "$type"; then
+              INVALID_FRAGMENTS="$INVALID_FRAGMENTS\n  - $filename (type: '$type')"
+            fi
+          done
+
+          if [ -n "$INVALID_FRAGMENTS" ]; then
+            echo "❌ Error: Invalid changelog fragment types found:"
+            echo -e "$INVALID_FRAGMENTS"
+            echo ""
+            echo "Valid types are: $VALID_TYPES"
+            echo "Example: 1234.added.md, 5678.fixed.md"
+            exit 1
+          fi
+
+          echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
+          echo "has_fragments=true" >> $GITHUB_OUTPUT
+
+      - name: Preview changelog
+        run: |
+          echo "## Preview of changelog for version ${{ inputs.version }}"
+          echo ""
+          uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}"
+
+      - name: Build changelog
+        run: |
+          uv run towncrier build --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}" --yes
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v7
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "Update changelog for version ${{ inputs.version }}"
+          title: "Release ${{ inputs.version }} - Changelog Update"
+          body: |
+            ## Changelog Update for Release ${{ inputs.version }}
+
+            This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
+
+            ### Summary
+            - **Version:** ${{ inputs.version }}
+            - **Date:** ${{ steps.set_date.outputs.release_date }}
+            - **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
+
+            ### What this PR does
+            - ✅ Adds new release section to CHANGELOG.md
+            - ✅ Removes processed changelog fragments
+            - ✅ Ready to merge for release
+
+            ### Next Steps
+            1. Review the changelog entries below
+            2. Make any necessary edits to CHANGELOG.md if needed
+            3. Merge this PR
+            4. Continue with your release process
+
+            ---
+
+            <details>
+            <summary>📋 Preview of changes</summary>
+
+            The changelog has been updated with entries from the following fragments:
+
+            ```bash
+            ${{ steps.check_fragments.outputs.fragment_count }} fragments processed
+            ```
+
+            </details>
+          branch: changelog-${{ inputs.version }}
+          delete-branch: true
+          labels: |
+            changelog
+            release

.github/workflows/python-compatibility.yaml

@@ -50,7 +50,6 @@ jobs:
         run: |
           uv sync --group dev --all-extras \
             --no-extra krisp \
-            --no-extra ultravox \
             --no-extra local-smart-turn \
             --no-extra moondream \
             --no-extra mlx-whisper

.readthedocs.yaml

@@ -11,7 +11,7 @@ build:
   jobs:
     post_install:
       - pip install uv
-      - UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
+      - UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
 
 sphinx:
   configuration: docs/api/conf.py

CHANGELOG.md

@@ -5,8 +5,740 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+<!-- towncrier release notes start -->
+
+## [0.0.98] - 2025-12-17
+
+### Added
+
+- Added `RimeNonJsonTTSService` which supports non-JSON streaming mode. This
+  new class supports websocket streaming for the Arcana model.
+  (PR [#3085](https://github.com/pipecat-ai/pipecat/pull/3085))
+
+- Added additional functionality related to "thinking", for Google and
+  Anthropic LLMs.
+
+  1. New typed parameters for Google and Anthropic LLMs that control the
+     models' thinking behavior (like how much thinking to do, and whether to
+     output thoughts or thought summaries):
+     - `AnthropicLLMService.ThinkingConfig`
+     - `GoogleLLMService.ThinkingConfig`
+  2. New frames for representing thoughts output by LLMs:
+     - `LLMThoughtStartFrame`
+     - `LLMThoughtTextFrame`
+     - `LLMThoughtEndFrame`
+  3. A generic mechanism for recording LLM thoughts to context, used
+     specifically to support Anthropic, whose thought signatures are expected
+     to appear alongside the text of the thoughts within assistant context
+     messages. See:
+     - `LLMThoughtEndFrame.signature`
+     - `LLMAssistantAggregator` handling of the above field
+     - `AnthropicLLMAdapter` handling of `"thought"` context messages
+  4. Google-specific logic for inserting thought signatures into the context,
+     to help maintain thinking continuity in a chain of LLM calls. See:
+     - `GoogleLLMService` sending `LLMMessagesAppendFrame`s to add
+       LLM-specific
+       `"thought_signature"` messages to context
+     - `GeminiLLMAdapter` handling of `"thought_signature"` messages
+  5. An expansion of `TranscriptProcessor` to process LLM thoughts in
+     addition to user and assistant utterances. See:
+     - `TranscriptProcessor(process_thoughts=True)` (defaults to `False`)
+     - `ThoughtTranscriptionMessage`, which is now also emitted with the
+       `"on_transcript_update"` event
+       (PR [#3175](https://github.com/pipecat-ai/pipecat/pull/3175))
+
+- Data and control frames can now be marked as non-interruptible by using the
+  `UninterruptibleFrame` mixin. Frames marked as `UninterruptibleFrame` will
+  not be interrupted during processing, and any queued frames of this type will
+  be retained in the internal queues. This is useful when you need ordered
+  frames (data or control) that should not be discarded or cancelled due to
+  interruptions.
+  (PR [#3189](https://github.com/pipecat-ai/pipecat/pull/3189))
+
+- Added `on_conversation_detected` event to `VoicemaiDetector`.
+  (PR [#3207](https://github.com/pipecat-ai/pipecat/pull/3207))
+
+- Added `x-goog-api-client` header with Pipecat's version to all Google
+  services' requests.
+  (PR [#3208](https://github.com/pipecat-ai/pipecat/pull/3208))
+
+- Added support for the HeyGen LiveAvatar API (see https://www.liveavatar.com/).
+  (PR [#3210](https://github.com/pipecat-ai/pipecat/pull/3210))
+
+- Added to `AWSNovaSonicLLMService` functionality related to the new (and now
+  default) Nova 2 Sonic model (`"amazon.nova-2-sonic-v1:0"`):
+
+  - Added the `endpointing_sensitivity` parameter to control how quickly the
+    model decides the user has stopped speaking.
+  - Made the assistant-response-trigger hack a no-op. It's only needed for
+    the older Nova Sonic model.
+    (PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
+
+- [Ultravox Realtime](https://docs.ultravox.ai) is now a supported
+  speech-to-speech service.
+
+  - Added `UltravoxRealtimeLLMService` for the integration.
+  - Added `49-ultravox-realtime.py` example (with tool calling).
+    (PR [#3227](https://github.com/pipecat-ai/pipecat/pull/3227))
+
+- Added Daily PSTN dial-in support to the development runner with `--dialin`
+  flag. This includes:
+
+  - `/daily-dialin-webhook` endpoint that handles incoming Daily PSTN webhooks
+  - Automatic Daily room creation with SIP configuration
+  - `DialinSettings` and `DailyDialinRequest` types in `pipecat.runner.types`
+    for type-safe dial-in data
+  - The runner now mimics Pipecat Cloud's dial-in webhook handling for local
+    development
+    (PR [#3235](https://github.com/pipecat-ai/pipecat/pull/3235))
+
+- Add Gladia session id to logs for `GladiaSTTService`.
+  (PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
+
+- Added `InworldHttpTTSService` which uses Inworld's HTTP based TTS service in
+  either streaming or non-streaming mode. Note: This class was previously named
+  `InworldTTSService`.
+  (PR [#3239](https://github.com/pipecat-ai/pipecat/pull/3239))
+
+- Added `language_hints_strict` parameter to `SonioxSTTService` to strictly
+  enforces language hints. This ensures that transcription occurs in the
+  specified language.
+  (PR [#3245](https://github.com/pipecat-ai/pipecat/pull/3245))
+
+- Added Pipecat library version info to the `about` field in the `bot-ready`
+  RTVI message.
+  (PR [#3248](https://github.com/pipecat-ai/pipecat/pull/3248))
+
+- Added `VisionFullResponseStartFrame`, `VisionFullResponseEndFrame` and
+  `VisionTextFrame`. This are used by vision services similar to LLM
+  services.
+  (PR [#3252](https://github.com/pipecat-ai/pipecat/pull/3252))
+
+### Changed
+
+- `FunctionCallInProgressFrame` and `FunctionCallResultFrame` have changed from
+  system frames to a control frame and a data frame, respectively, and are
+  now both marked as `UninterruptibleFrame`.
+  (PR [#3189](https://github.com/pipecat-ai/pipecat/pull/3189))
+
+- `UserBotLatencyLogObserver` now uses `VADUserStartedSpeakingFrame` and
+  `VADUserStoppedSpeakingFrame` to determine latency from user stopped speaking
+  to bot started speaking.
+  (PR [#3206](https://github.com/pipecat-ai/pipecat/pull/3206))
+
+- Updated `HeyGenVideoService` and `HeyGenTransport` to support both HeyGen
+  APIs (Interactive Avatar and Live Avatar).
+  Using them is as simple as specifying the `service_type` when creating the
+  `HeyGenVideoService` and the `HeyGenTransport`:
+
+  ```python
+  heyGen = HeyGenVideoService(
+      api_key=os.getenv("HEYGEN_LIVE_AVATAR_API_KEY"),
+      service_type=ServiceType.LIVE_AVATAR,
+      session=session,
+  )
+  ```
+
+  (PR [#3210](https://github.com/pipecat-ai/pipecat/pull/3210))
+
+- Made `"amazon.nova-2-sonic-v1:0"` the new default model for
+  `AWSNovaSonicLLMService`.
+  (PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
+
+- Updated the `run_inference` methods in the LLM service classes
+  (`AnthropicLLMService`, `AWSBedrockLLMService`, `GoogleLLMService`, and
+  `OpenAILLMService` and its base classes) to use the provided LLM
+  configuration parameters.
+  (PR [#3214](https://github.com/pipecat-ai/pipecat/pull/3214))
+
+- Updated default models for:
+
+  - `GeminiLiveLLMService` to `gemini-2.5-flash-native-audio-preview-12-2025`.
+  - `GeminiLiveVertexLLMService` to `gemini-live-2.5-flash-native-audio`.
+    (PR [#3228](https://github.com/pipecat-ai/pipecat/pull/3228))
+
+- Changed the `reason` field in `EndFrame`, `CancelFrame`, `EndTaskFrame`, and
+  `CancelTaskFrame` from `str` to `Any` to indicate that it can hold values
+  other than strings.
+  (PR [#3231](https://github.com/pipecat-ai/pipecat/pull/3231))
+
+- Updated websocket STT services to use the `WebsocketSTTService` base class.
+  This base class manages the websocket connection and handles reconnects.
+  Updated services:
+
+  - `AssemblyAISTTService`
+  - `AWSTranscribeSTTService`
+  - `GladiaSTTService`
+  - `SonioxSTTService`
+    (PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
+
+- Changed Inworld's TTS service implementations:
+
+  - Previously, the HTTP implementation was named `InworldTTSService`. That
+    has been moved to `InworldHttpTTSService`. This service now supports
+    word-timestamp alignment data in both streaming and non-streaming modes.
+  - Updated the `InworldTTSService` class to use Inworld's Websocket API.
+    This class now has support for word-timestamp alignment data and tracks
+    contexts for each user turn.
+    (PR [#3239](https://github.com/pipecat-ai/pipecat/pull/3239))
+
+- ⚠️ Breaking change: `WordTTSService.start_word_timestamps()` and
+  `WordTTSService.reset_word_timestamps()` are now async.
+  (PR [#3240](https://github.com/pipecat-ai/pipecat/pull/3240))
+
+- Updated the current RTVI version to 1.1.0 to reflect recent additions and
+  deprecations.
+
+  - New RTVI Messages: `send-text` and `bot-output`
+  - Deprecated Messages: `append-to-context` and `bot-transcription`
+    (PR [#3248](https://github.com/pipecat-ai/pipecat/pull/3248))
+
+- `MoondreamService` now pushes `VisionFullResponseStartFrame`,
+  `VisionFullResponseEndFrame` and `VisionTextFrame`.
+  (PR [#3252](https://github.com/pipecat-ai/pipecat/pull/3252))
+
+### Deprecated
+
+- `FalSmartTurnAnalyzer` and `LocalSmartTurnAnalyzer` are deprecated and will
+  be removed in a future version. Use `LocalSmartTurnAnalyzerV3` instead.
+  (PR [#3219](https://github.com/pipecat-ai/pipecat/pull/3219))
+
+### Removed
+
+- Removed the deprecated VLLM-based open source Ultravox STT service.
+  (PR [#3227](https://github.com/pipecat-ai/pipecat/pull/3227))
+
+### Fixed
+
+- Fixed a bug in `AWSNovaSonicLLMService` where we would mishandle cancelled
+  tool calls in the context, resulting in errors.
+  (PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
+
+- Better support conversation history with Gemini 2.5 Flash Image (model
+  "gemini-2.5-flash-image"). Prior to this fix, the model had no memory of
+  previous images it had generated, so it wouldn't be able to iterate on
+  them.
+  (PR [#3224](https://github.com/pipecat-ai/pipecat/pull/3224))
+
+- Support conversations with Gemini 3 Pro Image (model
+  "gemini-3-pro-image-preview"). Prior to this fix, after the model generated
+  an image the conversation would not be able to progress.
+  (PR [#3224](https://github.com/pipecat-ai/pipecat/pull/3224))
+
+- Fixed an issue where `ElevenLabsHttpTTSService` was not updating
+  voice settings when receiving a `TTSUpdateSettingsFrame`.
+  (PR [#3226](https://github.com/pipecat-ai/pipecat/pull/3226))
+
+- Fixed the return type for `SmallWebRTCRequestHandler.handle_web_request()`
+  function.
+  (PR [#3230](https://github.com/pipecat-ai/pipecat/pull/3230))
+
+- Fix a bug in LLM context audio content handling
+  (PR [#3234](https://github.com/pipecat-ai/pipecat/pull/3234))
+
+- In `GladiaSTTService`, reset the `_bytes_sent` counter on connecting the
+  websocket. This avoids unnecessary audio buffer trimming.
+  (PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
+
+- Fixed a TTS service word-timestamp issue that could cause generated
+  `TTSTextFrame` instances to have an incorrect pts (`pts = -1`).
+  (PR [#3240](https://github.com/pipecat-ai/pipecat/pull/3240))
+
+- Fixed an issue in `SimpleTextAggreagtor` where spaces were not being stripped
+  before returning the aggregation. This resulted in an extra space for TTS
+  services that don't support word-timestamp alignment data.
+  (PR [#3247](https://github.com/pipecat-ai/pipecat/pull/3247))
+
+## [0.0.97] - 2025-12-05
+
+### Added
+
+- Added new Gradium services, `GradiumSTTService` and `GradiumTTSService`, for
+  speech-to-text and text-to-speech functionality using Gradium's API.
+
+- Additions for `AsyncAITTSService` and `AsyncAIHttpTTSService`:
+
+  - Added new `languages`: `pt`, `nl`, `ar`, `ru`, `ro`, `ja`, `he`, `hy`,
+    `tr`, `hi`, `zh`.
+  - Updated the default model to `asyncflow_multilingual_v1.0` for improved
+    accuracy and broader language coverage.
+
+- Added optional tool and tool output filters for MCP services.
+
+### Changed
+
+- Updated Deepgram logging to include Deepgram request IDs for improved
+  debugging.
+
+- Text Aggregation Improvements:
+
+  - **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
+    `AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
+    enables the aggregator to return multiple results based on the provided
+    text.
+  - Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
+    `PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
+    the base class's sentence detection logic.
+
+- Improved interruption handling to prevent bots from repeating themselves. LLM
+  services that return multiple sentences in a single response (e.g.,
+  `GoogleLLMService`) are now split into individual sentences before being sent
+  to TTS. This ensures interruptions occur at sentence boundaries, preventing
+  the bot from repeating content after being interrupted during long responses.
+
+- Updated `AICFilter` to use Quail STT as the default model
+  (`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine
+  interaction (e.g., voice agents, speech-to-text) and operates at a native
+  sample rate of 16 kHz with fixed enhancement parameters.
+
+- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is
+  called with an exception, the file name and line number where the exception
+  occured are now logged.
+
+- Updated Smart Turn model weights to v3.1.
+
+- Smart Turn analyzer now uses the full context of the turn rather than just
+  the audio since VAD last triggered.
+
+- Updated `CartesiaSTTService` to return the full transcription `result` in the
+  `TranscriptionFrame` and `InterimTranscriptionFrame`. This provides access to
+  word timestamp data.
+
+- `HumeTTSService` changes:
+
+  - Added tracking headers (`X-Hume-Client-Name` and `X-Hume-Client-Version`)
+    to all requests made by `HumeTTSService` to the Hume API for better usage
+    tracking and analytics.
+  - Added `stop()` and `cancel()` cleanup methods to `HumeTTSService` to
+    properly close the HTTP client and prevent resource leaks.
+
+### Deprecated
+
+- NVIDIA Services name changes (all functionality is unchanged):
+
+  - `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
+  - `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
+  - `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
+  - Use `uv pip install pipecat-ai[nvidia]` instead of
+    `uv pip install pipecat-ai[riva]`
+
+- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer
+  has any effect. Noise gating is now handled automatically by the AIC VAD
+  system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.
+
+- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.
+
+### Fixed
+
+- Fixed bug in `PatternPairAggregator` where pattern handlers could be called
+  multiple times for `KEEP` or `AGGREGATE` patterns.
+
+- Fixed sentence aggregation to correctly handle ambiguous punctuation in
+  streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").
+
+- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was always
+  set to `us-east-1` when providing an AWS_REGION env var.
+
+- Fixed an issue in `SarvamTTSService` where the last sentence was not being
+  spoken. Now, audio is flushed when the TTS services receives the
+  `LLMFullResponseEndFrame` or `EndFrame`.
+
+- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was
+  incorrectly pushed after a functional call. This caused an issue with the
+  voice-ui-kit's conversational panel rending of the LLM output after a
+  function call.
+
+- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM
+  services.
+
+- Fixed an issue that caused `WebsocketService` instances to attempt
+  reconnection during shutdown.
+
+- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were
+  only reported on the first TTS generation per turn.
+
+## [0.0.96] - 2025-11-26 🦃 "Happy Thanksgiving!" 🦃
+
+### Added
+
+- Added `AWSBedrockAgentCoreProcessor` to support invoking an AgentCore-hosted
+  agent in a Pipecat pipeline.
+
+- Enhanced error handling across the framework:
+
+  - Added `on_error` callback to `FrameProcessor` for centralized error
+    handling.
+
+  - Renamed `push_error(error: ErrorFrame)` to `push_error_frame(error: ErrorFrame)`
+    for clarity.
+
+  - Added new `push_error` method for simplified error reporting:
+
+    ```python
+    async def push_error(error_msg: str,
+                         exception: Optional[Exception] = None,
+                         fatal: bool = False)
+    ```
+
+  - Standardized error logging by replacing `logger.exception` calls with
+    `logger.error` throughout the codebase.
+
+- Added `cache_read_input_tokens`, `cache_creation_input_tokens` and
+  `reasoning_tokens` to OTel spans for LLM call
+
+- Added `LiveKitRESTHelper` utility class for managing LiveKit rooms via REST API.
+
+- Added `DeepgramSageMakerSTTService` which connects to a SageMaker hosted
+  Deepgram STT model. Added `07c-interruptible-deepgram-sagemaker.py`
+  foundational example.
+
+- Added `SageMakerBidiClient` to connect to SageMaker hosted BiDi compatible
+  services.
+
+- Added support for `include_timestamps` and `enable_logging` in
+  `ElevenLabsRealtimeSTTService`. When `include_timestamps` is enabled,
+  timestamp data is included in the `TranscriptionFrame`'s `result`
+  parameter.
+
+- Added optional speaking rate control to `InworldTTSService`.
+
+- Introduced a new `AggregatedTextFrame` type to support passing text along with
+  an `aggregated_by` field to describe the type of text
+  included. `TTSTextFrame`s now inherit from `AggregatedTextFrame`. With this
+  inheritance, an observer can watch for `AggregatedTextFrame`s to accumlate the
+  perceived output and determine whether or not the text was spoken based on if
+  that frame is also a `TTSTextFrame`.
+
+  With this frame, the llm token stream can be transformed into custom
+  composable chunks, allowing for aggregation outside the TTS service. This
+  makes it possible to listen for or handle those aggregations and sets the
+  stage for doing things like composing a best effort of the perceived llm
+  output in a more digestable form and to do so whether or not it is processed
+  by a TTS or if even a TTS exists.
+
+- Introduced `LLMTextProcessor`: A new processor meant to allow customization
+  for how LLMTextFrames should be aggregated and considered. It's purpose is to
+  turn `LLMTextFrame`s into `AggregatedTextFrame`s. By default, a TTSService
+  will still aggregate `LLMTextFrame`s by sentence for the service to
+  consume. However, if you wish to override how the llm text is aggregated, you
+  should no longer override the TTS's internal text_aggregator, but instead,
+  insert this processor between your LLM and TTS in the pipeline.
+
+- New `bot-output` RTVI message to represent what the bot actually "says".
+
+  - The `RTVIObserver` now emits `bot-output` messages based off the new
+    `AggregatedTextFrame`s (`bot-tts-text` and `bot-llm-text` are still
+    supported and generated, but `bot-transcript` is now deprecated in lieu of
+    this new, more thorough, message).
+
+  - The new `RTVIBotOutputMessage` includes the fields:
+
+    - `spoken`: A boolean indicating whether the text was spoken by TTS
+
+    - `aggregated_by`: A string representing how the text was aggregated
+      ("sentence", "word", "my custom aggregation")
+
+  - Introduced new fields to `RTVIObserver` to support the new `bot-output`
+    messaging:
+
+    - `bot_output_enabled`: Defaults to True. Set to false to disable bot-output
+      messages.
+
+    - `skip_aggregator_types`: Defaults to `None`. Set to a list of strings that
+      match aggregation types that should not be included in bot-output
+      messages. (Ex. `credit_card`)
+
+  - Introduced new methods, `add_text_transformer()` and
+    `remove_text_transformer()`, to `RTVIObserver` to support providing (and
+    subsequently removing) callbacks for various types of aggregations (or all
+    aggregations with `*`) that can modify the text before being sent as a
+    `bot-output` or `tts-text` message. (Think obscuring the credit card or
+    inserting extra detail the client might want that the context doesn't need.)
+
+- In `MiniMaxHttpTTSService`:
+
+  - Added support for speech-2.6-hd and speech-2.6-turbo models
+
+  - Added languages: Afrikaans, Bulgarian, Catalan, Danish, Persian, Filipino,
+    Hebrew, Croatian, Hungarian, Malay, Norwegian, Nynorsk, Slovak, Slovenian,
+    Swedish, and Tamil
+
+  - Added new emotions: calm and fluent
+
+- Added `enable_logging` to `SimliVideoService` input parameters. It's disabled
+  by default.
+
+### Changed
+
+- Updated `FishAudioTTSService` default model to `s1`.
+
+- Updated `DeepgramTTSService` to use Deepgram's TTS websocket API. ⚠️ This is
+  a potential breaking change, which only affects you if you're self-hosting
+  `DeepgramTTSService`. The new service uses Websockets and improves TTFB
+  latency.
+
+- Updated `daily-python` to 0.22.0.
+
+- `BaseTextAggregator` changes:
+
+  Modified the BaseTextAggregator type so that when text gets aggregated,
+  metadata can be associated with it. Currently, that just means a `type`, so
+  that the aggregation can be classified or described. Changes made to support
+  this:
+
+  - ⚠️ IMPORTANT: Aggregators are now expected to strip leading/trailing white
+    space characters before returning their aggregation from `aggregation()` or
+    `.text`. This way all aggregators have a consistent contract allowing
+    downstream use to know how to stitch aggregations back together.
+
+  - Introduced a new `Aggregation` dataclass to represent both the aggregated
+    `text` and a string identifying the `type` of aggregation (ex. "sentence",
+    "word", "my custom aggregation")
+
+  - ⚠️ Breaking change: `BaseTextAggregator.text` now returns an `Aggregation`
+    (instead of `str`).
+
+    Before:
+
+    ```python
+    aggregated_text = myAggregator.text
+    ```
+
+    Now:
+
+    ```python
+    aggregated_text = myAggregator.text.text
+    ```
+
+  - ⚠️ Breaking change: `BaseTextAggregator.aggregate()` now returns
+    `Optional[Aggregation]` (instead of `Optional[str]`).
+
+    Before:
+
+    ```python
+    aggregation = myAggregator.aggregate(text)
+    print(f"successfully aggregated text: {aggregation}")
+    ```
+
+    Now:
+
+    ```python
+    aggregation = myAggregator.aggregate(text)
+    if aggregation:
+      print(f"successfully aggregated text: {aggregation.text}")
+    ```
+
+  - `SimpleTextAggregator`, `SkipTagsAggregator`, `PatternPairAggregator`
+    updated to produce/consume `Aggregation` objects.
+
+  - All uses of the above Aggregators have been updated accordingly.
+
+- Augmented the `PatternPairAggregator` so that matched patterns can be treated
+  as their own aggregation, taking advantage of the new. To that end:
+
+  - Introduced a new, preferred version of `add_pattern` to support a new option
+    for treating a match as a separate aggregation returned from
+    `aggregate()`. This replaces the now deprecated `add_pattern_pair` method
+    and you provide a `MatchAction` in lieu of the `remove_match` field.
+
+    - `MatchAction` enum: `REMOVE`, `KEEP`, `AGGREGATE`, allowing customization
+      for how a match should be handled.
+
+      - `REMOVE`: The text along with its delimiters will be removed from the
+        streaming text. Sentence aggregation will continue on as if this text
+        did not exist.
+
+      - `KEEP`: The delimiters will be removed, but the content between them
+        will be kept. Sentence aggregation will continue on with the internal
+        text included.
+
+      - `AGGREGATE`: The delimiters will be removed and the content between will
+        be treated as a separate aggregation. Any text before the start of the
+        pattern will be returned early, whether or not a complete sentence was
+        found. Then the pattern will be returned. Then the aggregation will
+        continue on sentence matching after the closing delimiter is found. The
+        content between the delimiters is not aggregated by sentence. It is
+        aggregated as one single block of text.
+
+    - `PatternMatch` now extends `Aggregation` and provides richer info to
+      handlers.
+
+  - ⚠️ Breaking change: The `PatternMatch` type returned to handlers registered
+    via `on_pattern_match` has been updated to subclass from the new
+    `Aggregation` type, which means that `content` has been replaced with
+    `text` and `pattern_id` has been replaced with `type`:
+
+    ```python
+    async dev on_match_tag(match: PatternMatch):
+       pattern = match.type # instead of match.pattern_id
+       text = match.text # instead of match.content
+    ```
+
+- `TextFrame` now includes the field `append_to_context` to support setting
+  whether or not the encompassing text should be added to the LLM context (by
+  the LLM assistant aggregator). It defaults to `True`.
+
+- `TTSService` base class updates:
+
+  - `TTSService`s now accept a new `skip_aggregator_types` to avoid speaking
+    certain aggregation types (now determined/returned by the aggregator)
+
+  - Introduced the ability to do a just-in-time transform of text before it gets
+    sent to the TTS service via callbacks you can set up via a new init field,
+    `text_transforms` or a new method `add_text_transformer()`. This makes it
+    possible to do things like introduce TTS-specific tags for spelling or
+    emotion or change the pronunciation of something on the
+    fly. `remove_text_transformer` has also been added to support removing a
+    registered transform callback.
+
+  - TTS services push `AggregatedTextFrame` in addition to `TTSTextFrame`s when
+    either an aggregation occurs that should not be spoken or when the TTS
+    service supports word-by-word timestamping. In the latter case, the
+    `TTSService` preliminarily generates an `AggregatedTextFrame`, aggregated by
+    sentence to generate the full sentence content as early as possible.
+
+- Updated `CartesiaTTSService`:
+
+  - Modified use of custom default text_aggregator to avoid deprecation warnings
+    and push users towards use of transformers or the `LLMTextProcessor`
+
+  - Added convenience methods for taking advantage of Cartesia's SSML tags:
+    spell, emotion, pauses, volume, and speed.
+
+- Updated `RimeTTSService`:
+
+  - Modified use of custom default text_aggregator to avoid deprecation warnings
+    and push users towards use of transformers or the `LLMTextProcessor`
+
+  - Added convenience methods for taking advantage of Rime's customization
+    options: spell, pauses, pronunciations, and inline speed control.
+
+### Deprecated
+
+- The TTS constructor field, `text_aggregator` is deprecated in favor of the new
+  `LLMTextProcessor`. TTSServices still have an internal aggregator for support
+  of default behavior, but if you want to override the aggregation behavior, you
+  should use the new processor.
+
+- The RTVI `bot-transcription` event is deprecated in favor of the new
+  `bot-output` message which is the canonical representation of bot output
+  (spoken or not). The code still emits a transcription message for backwards
+  compatibility while transition occurs.
+
+- Deprecated `add_pattern_pair` in the `PatternPairAggregator` which takes a
+  `pattern_id` and `remove_match` field in favor of the new `add_pattern` method
+  which takes a `type` and an `action`
+
+- `english_normalization` input parameter for `MiniMaxHttpTTSService` is
+  deprecated, use `test_normalization` instead.
+
+### Fixed
+
+- Fixed an issue in `AWSBedrockLLMService` where the `aws_region` arg was
+  always set to `us-east-1` when providing an AWS_REGION env var.
+
+- Fixed an issue with `DeepgramFluxSTTService` where it sometimes failed to reconnect.
+
+- Fixed an issue in `ElevenLabsRealtimeSTTService` where dynamic language
+  updates were not working.
+
+- Fixed an issue in `ElevenLabsRealtimeSTTService` where setting the sample
+  rate would result in transcripts failing.
+
+- Fixed `InworldTTSService` audio config payload to use camelCase keys expected
+  by the Inworld API.
+
+## [0.0.95] - 2025-11-18
+
+### Added
+
+- Added ai-coustics integrated VAD (`AICVADAnalyzer`) with `AICFilter` factory and
+  example wiring; leverages the enhancement model for robust detection with no
+  ONNX dependency or added processing complexity.
+
+- Added a watchdog to `DeepgramFluxSTTService` to prevent dangling tasks in case the
+  user was speaking and we stop receiving audio.
+
+- Introduced a minimum confidence parameter in `DeepgramFluxSTTService` to avoid
+  generating transcriptions below a defined threshold.
+
+- Added `ElevenLabsRealtimeSTTService` which implements the Realtime STT
+  service from ElevenLabs.
+
+- Added word-level timestamps support to Hume TTS service
+
+### Changed
+
+- ⚠️ Breaking change: `LLMContext.create_image_message()`,
+  `LLMContext.create_audio_message()`, `LLMContext.add_image_frame_message()`
+  and `LLMContext.add_audio_frames_message()` are now async methods. This fixes
+  an issue where the asyncio event loop would be blocked while encoding audio or
+  images.
+
+- `ConsumerProcessor` now queues frames from the producer internally instead of
+  pushing them directly. This allows us to subclass consumer processors and
+  manipulate frames before they are pushed.
+
+- `BaseTextFilter` only require subclasses to implement the `filter()` method.
+
+- Extracted the logic for retrying connections, and create a new `send_with_retry`
+  method inside `WebSocketService`.
+
+- Refactored `DeepgramFluxSTTService` to automatically reconnect if sending a
+  message fails.
+
+- Updated all STT and TTS services to use consistent error handling pattern with
+  `push_error()` method for better pipeline error event integration.
+
+- Added support for `maybe_capture_participant_camera()` and
+  `maybe_capture_participant_screen()` for `SmallWebRTCTransport` in the runner
+  utils.
+
+- Added Hindi support for Rime TTS services.
+
+- Updated `GeminiTTSService` to use Google Cloud Text-to-Speech streaming API
+  instead of the deprecated Gemini API. Now uses `credentials` /
+  `credentials_path` for authentication. The `api_key` parameter is deprecated.
+  Also, added support for `prompt` parameter for style instructions and
+  expressive markup tags. Significantly improved latency with streaming
+  synthesis.
+
+- Updated language mappings for the Google and Gemini TTS services to match
+  official documentation.
+
+### Deprecated
+
+- The `api_key` parameter in `GeminiTTSService` is deprecated. Use
+  `credentials` or `credentials_path` instead for Google Cloud authentication.
+
+### Fixed
+
+- Fixed a `SimliVideoService` connection issue.
+
+- Fixed an issue in the `Runner` where, when using `SmallWebRTCTransport`, the
+  `request_data` was not being passed to the `SmallWebRTCRunnerArguments` body.
+
+- Fixed subtle issue of assistant context messages ending up with double spaces
+  between words or sentences.
+
+- Fixed an issue where `NeuphonicTTSService` wasn't pushing `TTSTextFrame`s,
+  meaning assistant messages weren't being written to context.
+
+- Fixed an issue with OpenTelemetry where tracing wasn't correctly displaying
+  LLM completions and tools when using the universal `LLMContext`.
+
+- Fixed issue where `DeepgramFluxSTTService` failed to connect if passing a
+  `keyterm` or `tag` containing a space.
+
+- Prevented `HeyGenVideoService` from automatically disconnecting after 5 minutes.
+
 ## [0.0.94] - 2025-11-10
 
+### Changed
+
+- Added support for retrying `SpeechmaticsTTSService` when it returns a 503
+  error. Default values in `InputParams`.
+
 ### Deprecated
 
 - The `KrispFilter` is deprecated and will be removed in a future version. Use

COMMUNITY_INTEGRATIONS.md

@@ -79,7 +79,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 **Examples:**
 
-- [RivaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/riva/stt.py)
+- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
 - [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
 
 #### Key requirements:

CONTRIBUTING.md

@@ -17,24 +17,121 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
    git checkout -b your-branch-name
    ```
 4. **Make your changes**: Edit or add files as necessary.
-5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
-6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
+5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
+6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
+7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
 
 ```bash
 git commit -m "Description of your changes"
 ```
 
-7. **Push your changes**: Push your branch to your forked repository.
+8. **Push your changes**: Push your branch to your forked repository.
 
 ```bash
 git push origin your-branch-name
 ```
 
-8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
+9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
    > Important: Describe the changes you've made clearly!
 
 Our maintainers will review your PR, and once everything is good, your contributions will be merged!
 
+## Changelog Entries
+
+Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
+
+### Creating a Changelog Fragment
+
+1. Create a new file in the `changelog/` directory with this naming pattern:
+
+   ```
+   <PR_number>.<type>.md
+   ```
+
+2. Choose the appropriate type:
+
+   - `added.md` - New features
+   - `changed.md` - Changes in existing functionality
+   - `deprecated.md` - Soon-to-be removed features
+   - `removed.md` - Removed features
+   - `fixed.md` - Bug fixes
+   - `security.md` - Security fixes
+
+3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
+
+**Example files:**
+
+`changelog/1234.added.md`:
+
+```markdown
+- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
+```
+
+`changelog/5678.fixed.md`:
+
+```markdown
+- Fixed an issue where audio frames were dropped during high-load scenarios.
+```
+
+**For entries with nested bullets:**
+
+`changelog/1234.changed.md`:
+
+```markdown
+- Updated service configuration:
+
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+### Multiple Changes in One PR
+
+**Different types of changes:** Create separate fragment files for each type:
+
+```
+changelog/1234.added.md
+changelog/1234.fixed.md
+```
+
+**Multiple changes of the same type:** Create numbered fragment files:
+
+```
+changelog/1234.changed.md
+changelog/1234.changed.2.md
+```
+
+**Related changes:** Use nested bullets in a single fragment:
+
+```markdown
+- Updated service configuration:
+
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
+
+### Preview Your Changes
+
+To see what your changelog entry will look like:
+
+```bash
+towncrier build --draft --version Unreleased
+```
+
+This won't modify any files, just show you a preview.
+
+### When to Skip Changelog Entries
+
+You can skip adding a changelog entry for:
+
+- Documentation-only changes
+- Internal refactoring with no user-facing impact
+- Test-only changes
+- CI/build configuration changes
+
+If you're unsure whether your change needs a changelog entry, ask in your PR!
+
 ## Dependency Management
 
 This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.

README.md

@@ -3,7 +3,6 @@
 </div></h1>
 
 [![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/pipecat-ai/pipecat)
-[![](https://getmanta.ai/api/badges?text=Manta%20Graph&link=manta)](https://getmanta.ai/pipecat)
 
 # 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
 
@@ -74,10 +73,10 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
 
 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                          |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                          |
 | LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                                                                                              |
-| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
+| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), Ultravox,                                                                                                                                                                                                                                                                       |
 | Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 | Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
@@ -154,7 +153,6 @@ You can get started with Pipecat running on your local machine, then move your a
      --no-extra gstreamer \
      --no-extra krisp \
      --no-extra local \
-     --no-extra ultravox # (ultravox not fully supported on macOS)
    ```
 
 3. Install the git pre-commit hooks:

changelog/_template.md.j2

@@ -0,0 +1,16 @@
+{% for section, _ in sections.items() %}
+{% if sections[section] %}
+{% for category, val in definitions.items() if category in sections[section]%}
+### {{ definitions[category]['name'] }}
+
+{% for text, values in sections[section][category].items() %}
+{{ text }}
+(PR {{ values|join(', ') }})
+
+{% endfor %}
+{% endfor %}
+{% else %}
+No significant changes.
+
+{% endif %}
+{% endfor %}

docs/api/build-docs.sh

@@ -2,7 +2,7 @@
 
 # Build docs using uv
 echo "Installing dependencies with uv..."
-uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
+uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
 
 # Check if sphinx-build is available
 if ! uv run sphinx-build --version &> /dev/null; then
@@ -24,4 +24,4 @@ if [ $? -eq 0 ]; then
 else
     echo "Documentation build failed!" >&2
     exit 1
-fi
+fi

docs/api/conf.py

@@ -61,9 +61,6 @@ autodoc_mock_imports = [
     # OpenCV - sometimes has import issues during docs build
     "cv2",
     # Heavy ML packages excluded from ReadTheDocs
-    # ultravox dependencies
-    "vllm",
-    "vllm.engine.arg_utils",
     # local-smart-turn dependencies
     "coremltools",
     "coremltools.models",
@@ -119,7 +116,6 @@ def import_core_modules():
         "pipecat.observers",
         "pipecat.runner",
         "pipecat.serializers",
-        "pipecat.sync",
         "pipecat.transcriptions",
         "pipecat.utils",
     ]

docs/api/index.rst

@@ -30,7 +30,6 @@ Quick Links
    Runner <api/pipecat.runner>
    Serializers <api/pipecat.serializers>
    Services <api/pipecat.services>
-   Sync <api/pipecat.sync>
    Transcriptions <api/pipecat.transcriptions>
    Transports <api/pipecat.transports>
-   Utils <api/pipecat.utils>
+   Utils <api/pipecat.utils>

env.example

@@ -44,6 +44,7 @@ DAILY_SAMPLE_ROOM_URL=https://...
 
 # Deepgram
 DEEPGRAM_API_KEY=...
+SAGEMAKER_ENDPOINT_NAME=...
 
 # DeepSeek
 DEEPSEEK_API_KEY=...
@@ -72,6 +73,9 @@ GOOGLE_CLOUD_PROJECT_ID=...
 GOOGLE_CLOUD_LOCATION=...
 GOOGLE_TEST_CREDENTIALS=...
 
+# Gradium
+GRAPDIUM_API_KEY=...
+
 # Grok
 GROK_API_KEY=...
 
@@ -80,6 +84,7 @@ GROQ_API_KEY=...
 
 # Heygen
 HEYGEN_API_KEY=...
+HEYGEN_LIVE_AVATAR_API_KEY=...
 
 # Hume
 HUME_API_KEY=...
@@ -186,8 +191,11 @@ TOGETHER_API_KEY=...
 TWILIO_ACCOUNT_SID=...
 TWILIO_AUTH_TOKEN=...
 
+# Ultravox Realtime
+ULTRAVOX_API_KEY=...
+
 # WhatsApp
 WHATSAPP_TOKEN=...
 WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
 WHATSAPP_PHONE_NUMBER_ID=...
-WHATSAPP_APP_SECRET=...
+WHATSAPP_APP_SECRET=...

examples/foundational/01c-nvidia-riva-tts.py

@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.riva.tts import FastPitchTTSService
+from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -36,7 +36,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     task = PipelineTask(
         Pipeline([tts, transport.output()]),

examples/foundational/04-transports-small-webrtc.py

@@ -77,7 +77,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/04a-transports-daily.py

@@ -60,7 +60,7 @@ async def main():
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/04b-transports-livekit.py

@@ -69,7 +69,7 @@ async def main():
             "role": "system",
             "content": "You are a helpful LLM in a WebRTC call. "
             "Your goal is to demonstrate your capabilities in a succinct way. "
-            "Your output will be converted to audio so don't include special characters in your answers. "
+            "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
             "Respond to what the user said in a creative and helpful way.",
         },
     ]

examples/foundational/06-listen-and-respond.py

@@ -100,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/06a-image-sync.py

@@ -113,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07-interruptible-cartesia-http.py

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07-interruptible.py

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07a-interruptible-speechmatics-vad.py

@@ -121,7 +121,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 "content": (
                     "You are a helpful British assistant called Sarah. "
                     "Your goal is to demonstrate your capabilities in a succinct way. "
-                    "Your output will be converted to audio so don't include special characters in your answers. "
+                    "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
                     "Always include punctuation in your responses. "
                     "Give very short replies - do not give longer replies unless strictly necessary. "
                     "Respond to what the user said in a concise, funny, creative and helpful way. "

examples/foundational/07a-interruptible-speechmatics.py

@@ -111,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 "content": (
                     "You are a helpful British assistant called Sarah. "
                     "Your goal is to demonstrate your capabilities in a succinct way. "
-                    "Your output will be converted to audio so don't include special characters in your answers. "
+                    "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
                     "Always include punctuation in your responses. "
                     "Give very short replies - do not give longer replies unless strictly necessary. "
                     "Respond to what the user said in a concise, funny, creative and helpful way. "

examples/foundational/07aa-interruptible-soniox.py

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07ab-interruptible-inworld-http.py

@@ -4,7 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 import os
 
 import aiohttp
@@ -15,26 +14,26 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.inworld.tts import InworldTTSService
+from pipecat.services.inworld.tts import InworldHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -58,22 +57,18 @@ transport_params = {
 
 
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    logger.info(f"Starting bot")
+    logger.info("Starting bot")
 
-    # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        # Inworld TTS Service - Unified streaming and non-streaming
-        # Set streaming=True for real-time audio, streaming=False for complete audio generation
-        streaming = True  # Toggle this to switch between modes
-
-        tts = InworldTTSService(
+        tts = InworldHttpTTSService(
             api_key=os.getenv("INWORLD_API_KEY", ""),
             aiohttp_session=session,
             voice_id="Ashley",
             model="inworld-tts-1",
-            streaming=streaming,  # True: real-time chunks, False: complete audio then playback
+            # Set to False for non-streaming mode or True for streaming mode.
+            streaming=True,
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
@@ -81,22 +76,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
             },
         ]
 
         context = LLMContext(messages)
         context_aggregator = LLMContextAggregatorPair(context)
 
+        rtvi = RTVIProcessor()
+
         pipeline = Pipeline(
             [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                transport.input(),
+                rtvi,
+                stt,
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
             ]
         )
 
@@ -106,19 +104,27 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            observers=[
+                RTVIObserver(rtvi),
+                DebugLogObserver(
+                    frame_types={
+                        TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                    }
+                ),
+            ],
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")
         async def on_client_connected(transport, client):
-            logger.info(f"Client connected")
+            logger.info("Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
+            logger.info("Client disconnected")
             await task.cancel()
 
         runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

examples/foundational/07ab-interruptible-inworld.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.inworld.tts import InworldTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = InworldTTSService(
+        api_key=os.getenv("INWORLD_API_KEY", ""),
+        voice_id="Ashley",
+        model="inworld-tts-1",
+        temperature=1.1,
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            rtvi,
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        observers=[
+            RTVIObserver(rtvi),
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07ac-interruptible-asyncai-http.py

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07ac-interruptible-asyncai.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07ad-interruptible-aicoustics.py

@@ -15,7 +15,6 @@ from loguru import logger
 from pipecat.audio.filters.aic_filter import AICFilter
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
-from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -48,7 +47,7 @@ def _create_aic_filter() -> AICFilter:
 
     return AICFilter(
         license_key=license_key,
-        enhancement_level=1.0,
+        enhancement_level=0.5,
     )
 
 
@@ -56,27 +55,33 @@ def _create_aic_filter() -> AICFilter:
 # instantiated. The function will be called when the desired transport gets
 # selected.
 transport_params = {
-    "daily": lambda: DailyParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
-    "twilio": lambda: FastAPIWebsocketParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
-    "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
+    "daily": lambda: (
+        lambda aic: DailyParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
+    "twilio": lambda: (
+        lambda aic: FastAPIWebsocketParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
+    "webrtc": lambda: (
+        lambda aic: TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
 }
 
 
@@ -95,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07ae-interruptible-hume.py

@@ -13,24 +13,29 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+)
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
+
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets
 # selected.
@@ -72,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 
@@ -88,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             context_aggregator.user(),  # User responses
             llm,  # LLM
-            tts,  # TTS
+            tts,  # TTS (HumeTTSService with word timestamps)
             transport.output(),  # Transport bot output
             context_aggregator.assistant(),  # Assistant spoken responses
         ]
@@ -102,7 +107,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             audio_out_sample_rate=HUME_SAMPLE_RATE,
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-        observers=[RTVIObserver(rtvi)],
+        observers=[
+            RTVIObserver(rtvi),
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
     )
 
     @rtvi.event_handler("on_client_ready")
@@ -112,6 +124,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
+        logger.info(
+            "💡 Word timestamps are enabled! Watch the console for TTSTextFrame logs showing each word with its PTS."
+        )
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])

examples/foundational/07af-interruptible-gradium.py

@@ -4,7 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 import os
 
 from dotenv import load_dotenv
@@ -14,32 +13,23 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.ultravox.stt import UltravoxSTTService
+from pipecat.services.gradium.stt import GradiumSTTService
+from pipecat.services.gradium.tts import GradiumTTSService
+from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# NOTE: This example requires GPU resources to run efficiently.
-# The Ultravox model is compute-intensive and performs best with GPU acceleration.
-# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
-
-
-# Want to initialize the ultravox processor since it takes time to load the model and dont
-# want to load it every time the pipeline is run
-ultravox_processor = UltravoxSTTService(
-    model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
-    hf_token=os.getenv("HF_TOKEN"),
-)
-
-
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets
 # selected.
@@ -68,17 +58,34 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    tts = CartesiaTTSService(
-        api_key=os.environ.get("CARTESIA_API_KEY"),
-        voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
+    stt = GradiumSTTService(api_key=os.getenv("GRADIUM_API_KEY"))
+
+    tts = GradiumTTSService(
+        api_key=os.getenv("GRADIUM_API_KEY"),
+        voice_id="YTpq7expH9539ERJ",
     )
 
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
-            ultravox_processor,
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
     )
 
@@ -94,6 +101,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07c-interruptible-deepgram-flux.py

@@ -52,7 +52,10 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramFluxSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = DeepgramFluxSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
+    )
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
@@ -61,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07c-interruptible-deepgram-http.py

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07c-interruptible-deepgram-sagemaker.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.aws.llm import AWSBedrockLLMService
+from pipecat.services.deepgram.stt_sagemaker import DeepgramSageMakerSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Deepgram SageMaker STT Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram model
+    stt = DeepgramSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+    )
+
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+
+    llm = AWSBedrockLLMService(
+        aws_region=os.getenv("AWS_REGION"),
+        model="us.amazon.nova-pro-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07c-interruptible-deepgram.py

@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -79,7 +79,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07d-interruptible-elevenlabs.py

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.elevenlabs.stt import ElevenLabsRealtimeSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -60,7 +60,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
 
     tts = ElevenLabsTTSService(
         api_key=os.getenv("ELEVENLABS_API_KEY", ""),
@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07e-interruptible-playht-http.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07e-interruptible-playht.py

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07f-interruptible-azure-http.py

@@ -0,0 +1,135 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.azure.llm import AzureLLMService
+from pipecat.services.azure.stt import AzureSTTService
+from pipecat.services.azure.tts import AzureHttpTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = AzureSTTService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    tts = AzureHttpTTSService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    llm = AzureLLMService(
+        api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+        endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+        model=os.getenv("AZURE_CHATGPT_MODEL"),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07f-interruptible-azure.py

@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07g-interruptible-openai.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07h-interruptible-openpipe.py

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07i-interruptible-xtts.py

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07j-interruptible-gladia.py

@@ -81,7 +81,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07k-interruptible-lmnt.py

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07l-interruptible-groq.py

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07m-interruptible-aws-strands.py

@@ -71,9 +71,9 @@ def build_agent(model_id: str, max_tokens: int):
     @tool
     def check_weather(location: str) -> str:
         if location.lower() == "san francisco":
-            return "The weather in San Francisco is sunny and 30 degrees."
+            return "The weather in San Francisco is sunny and 75 degrees."
         elif location.lower() == "sydney":
-            return "The weather in Sydney is cloudy and 20 degrees."
+            return "The weather in Sydney is cloudy and 60 degrees."
         else:
             return "I'm not sure about the weather in that location."
 

examples/foundational/07m-interruptible-aws.py

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07n-interruptible-gemini-image.py

@@ -89,12 +89,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash-image",
+        # model="gemini-3-pro-image-preview", # A more powerful model, but slower
     )
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07n-interruptible-gemini.py

@@ -4,24 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""
-A conversational AI bot using Gemini for both LLM and TTS.
-
-This example demonstrates how to use Gemini's TTS capabilities with the new
-GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
-
-Features showcased:
-- Gemini LLM for conversation
-- Gemini TTS with natural voice control
-- Support for different voice personalities
-- Style and tone control through natural language prompts
-
-Run with:
-    python examples/foundational/gemini-tts.py
-
-Make sure to set your environment variables:
-    export GOOGLE_API_KEY=your_api_key_here
-"""
 
 import os
 
@@ -84,10 +66,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tts = GeminiTTSService(
-        api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash-preview-tts",  # TTS-specific model
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        model="gemini-2.5-flash-tts",
         voice_id="Charon",
-        params=GeminiTTSService.InputParams(language=Language.EN_US),
+        params=GeminiTTSService.InputParams(
+            language=Language.EN_US,
+            prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
+        ),
     )
 
     llm = GoogleLLMService(
@@ -101,15 +86,22 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             "role": "system",
             "content": """You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
 
-            IMPORTANT: Since you're using Gemini TTS which supports natural voice control, you can include speaking instructions in your responses. For example:
-            - "Say cheerfully: Welcome to our conversation!"
-            - "Read this in a calm, professional tone: Here are the details you requested."
-            - "Speak in an excited whisper: I have some great news to share!"
-            - "Say slowly and clearly: Let me explain this step by step."
+            IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
+            - [sigh] - Insert a sigh sound
+            - [laughing] - Insert a laugh
+            - [uhm] - Insert a hesitation sound
+            - [whispering] - Speak the next part in a whisper
+            - [shouting] - Speak the next part louder
+            - [extremely fast] - Speak the next part very quickly
+            - [short pause], [medium pause], [long pause] - Add pauses for dramatic effect
 
-            Feel free to use natural language instructions to control your voice style, tone, pace, and emotion. The TTS system will interpret these instructions and adjust the speech accordingly.
+            Examples:
+            - "Well [sigh] that's a tricky question."
+            - "[laughing] That's a great joke!"
+            - "[whispering] Let me tell you a secret."
+            - "The answer is... [long pause] ...42!"
 
-            Your output will be converted to audio, so avoid special characters in your answers. Respond to what the user said in a creative and helpful way.""",
+            Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.""",
         },
     ]
 
@@ -140,11 +132,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
-        # Kick off the conversation with a styled introduction
+        # Kick off the conversation
         messages.append(
             {
                 "role": "system",
-                "content": "Say cheerfully and warmly: Hello! I'm your AI assistant powered by Gemini's new TTS technology. I can speak with different voices, tones, and styles. How can I help you today?",
+                "content": "You are an AI assistant. You can help with a variety of tasks. Introduce yourself and ask the user what they would like to know.",
             }
         )
         await task.queue_frames([LLMRunFrame()])

examples/foundational/07n-interruptible-google-http.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GoogleHttpTTSService, GoogleTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        location="us",
+    )
+
+    tts = GoogleHttpTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User respones
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07n-interruptible-google.py

@@ -75,14 +75,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
     )
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07o-interruptible-assemblyai.py

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07p-interruptible-krisp-viva.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07p-interruptible-krisp.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07q-interruptible-rime-http.py

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07q-interruptible-rime.py

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07r-interruptible-nvidia.py

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.nim.llm import NimLLMService
-from pipecat.services.riva.stt import RivaSTTService
-from pipecat.services.riva.tts import RivaTTSService
+from pipecat.services.nvidia.llm import NvidiaLLMService
+from pipecat.services.nvidia.stt import NvidiaSTTService
+from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,16 +59,18 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = RivaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+    stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-    llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct")
+    llm = NvidiaLLMService(
+        api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
+    )
 
-    tts = RivaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07s-interruptible-google-audio-in.py

@@ -53,7 +53,7 @@ You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief i
 You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
 asked to transcribe what the user said, output an exact, word-for-word transcription.
 
-Your output will be converted to audio so don't include special characters in your answers.
+Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
 
 Each time you answer, you should respond in three parts.
 
@@ -224,8 +224,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
     )
 
     tts = GoogleTTSService(

examples/foundational/07t-interruptible-fish.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07v-interruptible-neuphonic.py

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07w-interruptible-fal.py

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07x-interruptible-local.py

@@ -56,7 +56,7 @@ async def main():
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/07y-interruptible-minimax.py

@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 

examples/foundational/07z-interruptible-sarvam-http.py

@@ -15,6 +15,7 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,7 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
             },
         ]
 
@@ -112,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

examples/foundational/07z-interruptible-sarvam.py

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/08-custom-frame-processor.py

@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/11-sound-effects.py

@@ -121,7 +121,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/12-describe-image-openai.py

@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
         },
     ]
 
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         # Kick off the conversation.
         image = Image.open(image_path)
-        message = LLMContext.create_image_message(
+        message = await LLMContext.create_image_message(
             image=image.tobytes(),
             format="RGB",
             size=image.size,

examples/foundational/12a-describe-image-anthropic.py

@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
         },
     ]
 
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         # Kick off the conversation.
         image = Image.open(image_path)
-        message = LLMContext.create_image_message(
+        message = await LLMContext.create_image_message(
             image=image.tobytes(),
             format="RGB",
             size=image.size,

examples/foundational/12b-describe-image-aws.py

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
         },
     ]
 
@@ -117,7 +117,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         # Kick off the conversation.
         image = Image.open(image_path)
-        message = LLMContext.create_image_message(
+        message = await LLMContext.create_image_message(
             image=image.tobytes(),
             format="RGB",
             size=image.size,

examples/foundational/12c-describe-image-gemini-flash.py

@@ -66,7 +66,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
         },
     ]
 
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         # Kick off the conversation.
         image = Image.open(image_path)
-        message = LLMContext.create_image_message(
+        message = await LLMContext.create_image_message(
             image=image.tobytes(),
             format="RGB",
             size=image.size,

examples/foundational/14-function-calling.py

@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14c-function-calling-together.py

@@ -106,7 +106,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14d-function-calling-anthropic-video.py

@@ -119,7 +119,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
         },
     ]
 

examples/foundational/14d-function-calling-aws-video.py

@@ -126,7 +126,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
         },
     ]
 

examples/foundational/14d-function-calling-gemini-flash-video.py

@@ -119,7 +119,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
         },
     ]
 

examples/foundational/14d-function-calling-moondream-video.py

@@ -15,14 +15,21 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame, UserImageRequestFrame
+from pipecat.frames.frames import (
+    Frame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMRunFrame,
+    TextFrame,
+    UserImageRequestFrame,
+)
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.processors.frame_processor import FrameDirection
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
     create_transport,
@@ -66,6 +73,27 @@ async def fetch_user_image(params: FunctionCallParams):
     # await params.result_callback({"result": "Image is being captured."})
 
 
+class MoondreamTextFrameWrapper(FrameProcessor):
+    """Wraps Moondream-provided TextFrames with LLM response start/end frames.
+
+    This processor detects TextFrames and automatically wraps them with
+    LLMFullResponseStartFrame and LLMFullResponseEndFrame to provide proper
+    response boundaries for downstream processors.
+    """
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        # If we receive a TextFrame, wrap it with response start/end frames
+        if isinstance(frame, TextFrame):
+            await self.push_frame(LLMFullResponseStartFrame(), direction)
+            await self.push_frame(frame, direction)
+            await self.push_frame(LLMFullResponseEndFrame(), direction)
+        else:
+            # For all other frames, just pass them through
+            await self.push_frame(frame, direction)
+
+
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets
 # selected.
@@ -120,7 +148,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
         },
     ]
 
@@ -130,6 +158,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # If you run into weird description, try with use_cpu=True
     moondream = MoondreamService()
 
+    # Wrap TextFrames with LLM response start/end frames, which makes Moondream
+    # output be treated like LLM responses for the purpose of context
+    # aggregation. Without this, the assistant context aggregator would ignore
+    # Moondream output (if the TTS service is disabled).
+    moondream_text_wrapper = MoondreamTextFrameWrapper()
+
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
@@ -137,7 +171,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             context_aggregator.user(),  # User responses
             ParallelPipeline(
                 [llm],  # LLM
-                [moondream],
+                [moondream, moondream_text_wrapper],
             ),
             tts,  # TTS
             transport.output(),  # Transport bot output

examples/foundational/14d-function-calling-openai-video.py

@@ -119,7 +119,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
         },
     ]
 

examples/foundational/14f-function-calling-groq.py

@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14g-function-calling-grok.py

@@ -99,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14h-function-calling-azure.py

@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14i-function-calling-fireworks.py

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = FireworksLLMService(
         api_key=os.getenv("FIREWORKS_API_KEY"),
-        model="accounts/fireworks/models/llama-v3p1-405b-instruct",
+        model="accounts/fireworks/models/gpt-oss-20b",
     )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. Start by saying hello.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. Start by saying hello.",
         },
     ]
 

examples/foundational/14j-function-calling-nvidia.py

@@ -27,7 +27,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.nim.llm import NimLLMService
+from pipecat.services.nvidia.llm import NvidiaLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -75,11 +75,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # text_filters=[MarkdownTextFilter()],
     )
 
-    llm = NimLLMService(
+    llm = NvidiaLLMService(
         api_key=os.getenv("NVIDIA_API_KEY"),
         model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
         # Recommended when turning thinking off
-        params=NimLLMService.InputParams(temperature=0.0),
+        params=NvidiaLLMService.InputParams(temperature=0.0),
     )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
@@ -112,7 +112,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         {"role": "system", "content": "/no_think"},
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14m-function-calling-openrouter.py

@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14n-function-calling-perplexity.py

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "user",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but try to be brief.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way, but try to be brief.",
         },
     ]
 

examples/foundational/14q-function-calling-qwen.py

@@ -105,7 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14r-function-calling-aws.py

@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14s-function-calling-sambanova.py

@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14t-function-calling-direct.py

@@ -106,7 +106,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14u-function-calling-ollama.py

@@ -122,7 +122,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14v-function-calling-openai.py

@@ -128,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14w-function-calling-mistral.py

@@ -116,7 +116,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/14x-function-calling-openpipe.py

@@ -126,7 +126,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/16-gpu-container-local-bot.py

@@ -82,7 +82,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/17-detect-user-idle.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         },
     ]
 

examples/foundational/19-openai-realtime.py

@@ -14,20 +14,13 @@ from loguru import logger
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.adapters.services.open_ai_realtime_adapter import OpenAIRealtimeLLMAdapter
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import (
-    LLMRunFrame,
-    LLMSetToolsFrame,
-    LLMUpdateSettingsFrame,
-    TranscriptionMessage,
-)
+from pipecat.frames.frames import LLMRunFrame, LLMSetToolsFrame, TranscriptionMessage
 from pipecat.observers.loggers.transcription_log_observer import TranscriptionLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments

examples/foundational/19a-azure-realtime.py

@@ -19,7 +19,6 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport