Add error handling for unsupported files

This PR introduces:
1. a new /files/ POST endpoint in the local runner that supports
   uploading a file to a folder that must be provided at runtime
2. By default, the runner will allow a maximum 10 files to be
   saved
3. Added logic to the send-file handler in RTVI to read a file
   from disk if the file provide is a url starting with '/files/'

.claude/skills/cleanup/SKILL.md

@@ -144,7 +144,7 @@ class InputParams(BaseModel):
 
 #### Examples
 
-Validated against `examples/07-interruptible.py`:
+Validated against `examples/foundational/07-interruptible.py`:
 
 - Proper `create_transport()` usage
 - Correct pipeline structure

.github/workflows/python-compatibility.yaml

@@ -42,7 +42,7 @@ jobs:
 
       - name: Test uv sync with all extras
         run: |
-          uv sync --group dev --all-extras
+          uv sync --group dev --all-extras --no-extra krisp
 
       - name: Verify installation
         run: |

.github/workflows/sync-quickstart.yaml

@@ -0,0 +1,51 @@
+name: Sync Quickstart to pipecat-quickstart repo
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'examples/quickstart/**'
+  workflow_dispatch: # Manual trigger
+
+jobs:
+  sync-quickstart:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout main repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Checkout quickstart repo
+        uses: actions/checkout@v4
+        with:
+          repository: pipecat-ai/pipecat-quickstart
+          token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
+          path: quickstart-repo
+
+      - name: Sync files (excluding uv.lock and README.md)
+        run: |
+          # Copy all files except uv.lock and README.md
+          find examples/quickstart -type f \
+            -not -name "README.md" \
+            -not -name "uv.lock" \
+            -exec cp {} quickstart-repo/ \;
+
+      - name: Commit and push changes
+        run: |
+          cd quickstart-repo
+          git config user.name "GitHub Action"
+          git config user.email "action@github.com"
+          git add .
+
+          # Only commit if there are changes
+          if ! git diff --staged --quiet; then
+            git commit -m "Sync from pipecat main repo
+            
+            Updated files from examples/quickstart/
+            Commit: ${{ github.sha }}
+            "
+            git push
+          else
+            echo "No changes to sync"
+          fi

.pre-commit-config.yaml

@@ -1,13 +1,8 @@
 repos:
-  - repo: local
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.1
     hooks:
       - id: ruff
-        name: ruff
-        entry: uv run ruff check --fix
-        language: system
-        types: [python]
+        language_version: python3
+        args: [--fix]
       - id: ruff-format
-        name: ruff-format
-        entry: uv run ruff format
-        language: system
-        types: [python]

.readthedocs.yaml

@@ -11,7 +11,7 @@ build:
   jobs:
     post_install:
       - pip install uv
-      - UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
+      - UV_PROJECT_ENVIRONMENT=$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

@@ -7,618 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- towncrier release notes start -->
 
-## [0.0.108] - 2026-03-27
-
-### Added
-
-- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`,
-  `sarvam-105b` and `sarvam-105b-32k`.
-  (PR [#3978](https://github.com/pipecat-ai/pipecat/pull/3978))
-
-- Added `on_turn_context_created(context_id)` hook to `TTSService`. Override
-  this to perform provider-specific setup (e.g. eagerly opening a server-side
-  context) before text starts flowing. Called each time a new turn context ID
-  is created.
-  (PR [#4013](https://github.com/pipecat-ai/pipecat/pull/4013))
-
-- Added `XAIHttpTTSService` for text-to-speech using xAI's HTTP TTS API.
-  (PR [#4031](https://github.com/pipecat-ai/pipecat/pull/4031))
-
-- Added support for "developer" role messages in conversation context across
-  all LLM adapters. For non-OpenAI services (Anthropic, Google, AWS Bedrock),
-  "developer" messages are converted to "user" messages (use
-  `system_instruction` to set the system instruction). For OpenAI services,
-  "developer" messages pass through in conversation history. For the Responses
-  API, they are kept as "developer" role (matching the existing "system" →
-  "developer" conversion).
-  (PR [#4089](https://github.com/pipecat-ai/pipecat/pull/4089))
-
-- Added `SmallestTTSService`, a WebSocket-based TTS service integration with
-  Smallest AI's Waves API. Supports the Lightning v2 and v3.1 models with
-  configurable voice, language, speed, consistency, similarity, and enhancement
-  settings.
-  (PR [#4092](https://github.com/pipecat-ai/pipecat/pull/4092))
-
-- Added warnings in turn stop strategies when `VADParams.stop_secs` differs
-  from the recommended default (0.2s) or when `stop_secs >= STT p99 latency`,
-  which collapses the STT wait timeout to 0s and may cause delayed turn
-  detection. The warnings guide developers to re-run the
-  [stt-benchmark](https://github.com/pipecat-ai/stt-benchmark) with their VAD
-  settings.
-  (PR [#4115](https://github.com/pipecat-ai/pipecat/pull/4115))
-
-- Added `domain` parameter to `AssemblyAISTTSettings` for specialized
-  recognition modes such as Medical Mode (`domain="medical-v1"`).
-  (PR [#4117](https://github.com/pipecat-ai/pipecat/pull/4117))
-
-- Added `NovitaLLMService` for using Novita AI's LLM models via their
-  OpenAI-compatible API.
-  (PR [#4119](https://github.com/pipecat-ai/pipecat/pull/4119))
-
-- Added `cleanup()` method to `VADAnalyzer` and `VADController` so VAD analyzer
-  resources are properly released when no longer needed. Custom `VADAnalyzer`
-  subclasses can override `cleanup()` to free any held resources.
-  (PR [#4120](https://github.com/pipecat-ai/pipecat/pull/4120))
-
-- Added `on_end_of_turn` event handler to `AssemblyAISTTService`. This fires
-  after the final transcript is pushed, providing a reliable hook for
-  end-of-turn logic that doesn't race with `TranscriptionFrame`. Works in both
-  Pipecat and AssemblyAI turn detection modes.
-  (PR [#4128](https://github.com/pipecat-ai/pipecat/pull/4128))
-
-- Added `DeepgramFluxSageMakerSTTService` for running Deepgram Flux
-  speech-to-text on AWS SageMaker endpoints.  Use with
-  `ExternalUserTurnStrategies` to take advantage of Flux's turn detection.
-  (PR [#4143](https://github.com/pipecat-ai/pipecat/pull/4143))
-
-- Added `Mem0MemoryService.get_memories()` convenience method for retrieving
-  all stored memories outside the pipeline (e.g. to build a personalized
-  greeting at connection time). This avoids the need to manually handle client
-  type branching, filter construction, and async wrapping.
-  (PR [#4156](https://github.com/pipecat-ai/pipecat/pull/4156))
-
-### Changed
-
-- Added context prewarming path for `InworldTTSService` to improve first audio
-  latency.
-  (PR [#4013](https://github.com/pipecat-ai/pipecat/pull/4013))
-
-- Added `KrispVivaVadAnalyzer` for Voice Activity Detection using the Krisp
-  VIVA SDK (requires `krisp_audio`).
-  (PR [#4022](https://github.com/pipecat-ai/pipecat/pull/4022))
-
-- Modified `InworldTTSService` to close context at end of turn instead of
-  relying on idle timeout.
-  (PR [#4028](https://github.com/pipecat-ai/pipecat/pull/4028))
-
-- Added Gemini 3 support to the Gemini Live service.
-  (PR [#4078](https://github.com/pipecat-ai/pipecat/pull/4078))
-
-- `TTSService`: the default `stop_frame_timeout_s` (idle time before an
-  automatic `TTSStoppedFrame` is pushed when `push_stop_frames=True`) has
-  changed from `2.0` to `3.0` seconds.
-  (PR [#4084](https://github.com/pipecat-ai/pipecat/pull/4084))
-
-- ⚠️ `GeminiLLMAdapter` now only treats `messages[0]` as the initial system
-  message, matching all other adapters. Previously it searched for the first
-  "system" message anywhere in the conversation history. A "system" message
-  appearing later in the list will now be converted to "user" instead of being
-  extracted as the system instruction.
-  (PR [#4089](https://github.com/pipecat-ai/pipecat/pull/4089))
-
-- Fixed `InworldTtsService` to fallback to full text when TTS timestamps are
-  not received.
-  (PR [#4113](https://github.com/pipecat-ai/pipecat/pull/4113))
-
-- ⚠️ Realtime services (Gemini Live, OpenAI Realtime, Grok Realtime, Nova
-  Sonic) now prefer `system_instruction` from service settings over an initial
-  system message in the LLM context, matching the behavior of non-realtime
-  services. Previously, context-provided system instructions took precedence. A
-  warning is now logged when both are set.
-  (PR [#4130](https://github.com/pipecat-ai/pipecat/pull/4130))
-
-- Bumped `nvidia-riva-client` minimum version to `>=2.25.1`.
-  (PR [#4136](https://github.com/pipecat-ai/pipecat/pull/4136))
-
-- Upgraded `protobuf` from 5.x to 6.x (`>=6.31.1,<7`).
-  (PR [#4136](https://github.com/pipecat-ai/pipecat/pull/4136))
-
-- Unrecognized language strings (e.g. Deepgram's `"multi"`) no longer produce a
-  warning at startup. The log message has been downgraded to debug level since
-  these are valid service-specific values that are passed through correctly.
-  (PR [#4137](https://github.com/pipecat-ai/pipecat/pull/4137))
-
-- `GrokLLMService` and `GrokRealtimeLLMService` now live in the
-  `pipecat.services.xai` module alongside `XAIHttpTTSService`, since all three
-  use the same xAI API. Update imports from `pipecat.services.grok.*` to
-  `pipecat.services.xai.*` (e.g. `from pipecat.services.xai.llm import
-  GrokLLMService`).
-  (PR [#4142](https://github.com/pipecat-ai/pipecat/pull/4142))
-
-- ⚠️ Bumped `mem0ai` dependency from `~=0.1.94` to `>=1.0.8,<2`. Users of the
-  `mem0` extra will need to update their mem0ai package.
-  (PR [#4156](https://github.com/pipecat-ai/pipecat/pull/4156))
-
-### Deprecated
-
-- `pipecat.services.grok.llm`, `pipecat.services.grok.realtime.llm`, and
-  `pipecat.services.grok.realtime.events` are deprecated. The old import paths
-  still work but emit a `DeprecationWarning`; use `pipecat.services.xai.llm`,
-  `pipecat.services.xai.realtime.llm`, and
-  `pipecat.services.xai.realtime.events` instead.
-  (PR [#4142](https://github.com/pipecat-ai/pipecat/pull/4142))
-
-### Removed
-
-- ⚠️ `TTSService.add_word_timestamps()` no longer supports the `"Reset"` and
-  `"TTSStoppedFrame"` sentinel strings. If you have a custom TTS service that
-  called `await self.add_word_timestamps([("Reset", 0)])` or `await
-  self.add_word_timestamps([("TTSStoppedFrame", 0), ("Reset", 0)], ctx_id)`,
-  replace them with `await self.append_to_audio_context(ctx_id,
-  TTSStoppedFrame(context_id=ctx_id))` and let `_handle_audio_context` manage
-  the word-timestamp reset automatically.
-  (PR [#4145](https://github.com/pipecat-ai/pipecat/pull/4145))
-
-- Removed `SambaNovaSTTService`. SambaNova no longer offers speech-to-text
-  audio models. Use another STT provider instead.
-  (PR [#4154](https://github.com/pipecat-ai/pipecat/pull/4154))
-
-### Fixed
-
-- Fixed Gemini Live (`GoogleGeminiLiveLLMService`) not honoring
-  `settings.system_instruction`. The system instruction was being read from a
-  deprecated constructor parameter instead of the settings object, causing it
-  to be silently ignored.
-  (PR [#4089](https://github.com/pipecat-ai/pipecat/pull/4089))
-
-- Fixed `AWSBedrockLLMAdapter` sending an empty message list to the API when
-  the only message in context was a system message. The lone system message is
-  now converted to "user" role instead of being extracted, matching the
-  existing Anthropic adapter behavior.
-  (PR [#4089](https://github.com/pipecat-ai/pipecat/pull/4089))
-
-- Fixed Gemini Live pipeline hanging indefinitely when an `EndFrame` was
-  deferred while waiting for the bot to finish responding and `turn_complete`
-  never arrived. As a possible root-cause fix, `turn_complete` messages are now
-  handled even if they lack `usage_metadata`. As a fallback, the deferred
-  `EndFrame` now has a 30-second safety timeout.
-  (PR [#4125](https://github.com/pipecat-ai/pipecat/pull/4125))
-
-- Fixed ElevenLabs WebSocket disconnections (1008 "Maximum simultaneous
-  contexts exceeded") caused by rapid user interruptions. When interruptions
-  arrived before any TTS text was generated, phantom contexts were created on
-  the ElevenLabs server that were never closed, eventually exceeding the
-  5-context limit.
-  (PR [#4126](https://github.com/pipecat-ai/pipecat/pull/4126))
-
-- Fixed the final sentence being dropped from the conversation context when
-  using RTVI text input with non-word-timestamp TTS services. The
-  `LLMFullResponseEndFrame` was racing ahead of the last `TTSTextFrame`,
-  causing the `LLMAssistantAggregator` to finalize the context before the final
-  sentence arrived.
-  (PR [#4127](https://github.com/pipecat-ai/pipecat/pull/4127))
-
-- Fixed audio crackling and popping in recordings when both user and bot are
-  speaking. `AudioBufferProcessor` no longer injects silence into a track's
-  buffer while that track is actively producing audio, preventing mid-utterance
-  interruptions in the recorded output.
-  (PR [#4135](https://github.com/pipecat-ai/pipecat/pull/4135))
-
-- Fixed websocket TTS word timestamps so interrupted contexts cannot leak stale
-  words or backward PTS values into later turns.
-  (PR [#4145](https://github.com/pipecat-ai/pipecat/pull/4145))
-
-- Fixed a race condition in `InterruptibleTTSService` where, if `run_tts` had
-  been invoked but `BotStartedSpeakingFrame` had not yet been received, a user
-  interruption could allow stale audio to leak through.
-  (PR [#4145](https://github.com/pipecat-ai/pipecat/pull/4145))
-
-- Fixed Gemini Live local VAD mode (`GeminiVADParams(disabled=True)` with
-  external VAD) not working. The bot now correctly detects user speech and
-  signals turn boundaries to the Gemini API.
-  (PR [#4146](https://github.com/pipecat-ai/pipecat/pull/4146))
-
-- Fixed Gemini Live message handling to process all `server_content` fields
-  independently. Gemini 3.x can bundle multiple fields (e.g. `model_turn` and
-  `output_transcription`) on the same message, but the previous `elif` chain
-  only processed the first match, silently dropping the rest.
-  (PR [#4147](https://github.com/pipecat-ai/pipecat/pull/4147))
-
-- Fixed `ServiceSwitcher` with `ServiceSwitcherStrategyFailover` incorrectly
-  triggering failover when `ErrorFrame`s from other pipeline stages (e.g. TTS)
-  propagated upstream through the switcher. Previously, any non-fatal error
-  passing through would be misattributed to the active service and trigger an
-  unwanted service switch. Now only errors originating from the switcher's own
-  managed services trigger failover.
-  (PR [#4149](https://github.com/pipecat-ai/pipecat/pull/4149))
-
-- Fixed `LiveKitOutputTransport` not clearing the `rtc.AudioSource` internal
-  buffer on interruption, causing the bot to continue speaking for several
-  seconds after being interrupted.
-  (PR [#4151](https://github.com/pipecat-ai/pipecat/pull/4151))
-
-- Fixed a crash in OpenAI LLM processing when the provider returns
-  `chunk.choices[0].delta.audio = None`, which caused `'NoneType' object has no
-  attribute 'get'` errors during audio transcript handling.
-  (PR [#4152](https://github.com/pipecat-ai/pipecat/pull/4152))
-
-- Fixed error floods in `DeepgramSTTService` when the WebSocket connection
-  drops. With Deepgram SDK 6.x, `send_media()` raises exceptions on a dead
-  connection instead of silently failing, causing every queued audio frame to
-  log an error. Now `send_media()` failures are caught gracefully — a single
-  warning is logged and audio frames are skipped until the existing
-  reconnection logic restores the connection.
-  (PR [#4153](https://github.com/pipecat-ai/pipecat/pull/4153))
-
-- `Mem0MemoryService` no longer blocks the event loop during memory storage and
-  retrieval. All Mem0 API calls now run in a background thread, and message
-  storage is fire-and-forget so it doesn't delay downstream processing.
-  (PR [#4156](https://github.com/pipecat-ai/pipecat/pull/4156))
-
-- Fixed `Mem0MemoryService` failing to store messages when the context
-  contained system or developer role messages. The Mem0 API only accepts user
-  and assistant roles, so other roles are now filtered out before storing.
-  (PR [#4156](https://github.com/pipecat-ai/pipecat/pull/4156))
-
-- Added missing `on_dtmf_event` callback to `LemonSliceTransportClient.setup()`
-  `DailyCallbacks` construction, fixing a `ValidationError` at pipeline setup
-  time.
-  (PR [#4161](https://github.com/pipecat-ai/pipecat/pull/4161))
-
-- Fixed an issue in `InworldTTSService` where, in cases of fast interruption,
-  we would continue receiving audio from the previous context.
-  (PR [#4167](https://github.com/pipecat-ai/pipecat/pull/4167))
-
-- Fixed a word timestamp interleaving issue in `InworldTTSService` when
-  processing multiple sentences.
-  (PR [#4167](https://github.com/pipecat-ai/pipecat/pull/4167))
-
-- Fixed duplicate `TTSStoppedFrame` being pushed in TTS services using
-  `push_stop_frames=True`. When the stop-frame timeout fired, a second
-  `TTSStoppedFrame` could be pushed after the normal one at context completion.
-  (PR [#4172](https://github.com/pipecat-ai/pipecat/pull/4172))
-
-- ⚠️ Fixed `DeepgramSTTService` compatibility with deepgram-sdk 6.1.0. The SDK
-  now requires explicit message objects for `send_keep_alive()`,
-  `send_close_stream()`, and `send_finalize()`. The minimum deepgram-sdk
-  version is now 6.1.0.
-  (PR [#4174](https://github.com/pipecat-ai/pipecat/pull/4174))
-
-- Fixed RTVI events not being delivered to clients when using WebSocket
-  transports. `ProtobufFrameSerializer` now sets `ignore_rtvi_messages=False`
-  by default.
-  (PR [#4176](https://github.com/pipecat-ai/pipecat/pull/4176))
-
-- Fixed a timing issue where turn detection timer tasks (idle controller,
-  speech timeout, turn analyzer, and turn completion) could miss their first
-  tick because the newly created asyncio task was not yet scheduled when the
-  caller continued.
-  (PR [#4183](https://github.com/pipecat-ai/pipecat/pull/4183))
-
-- Fixed `FastAPIWebsocketTransport` intermittently hanging on shutdown when the
-  remote side (e.g. Twilio) disconnects while audio is being sent. A race
-  condition between the send and receive paths could cause the
-  `on_client_disconnected` callback to be skipped, leaving the pipeline waiting
-  for a disconnect signal that never came.
-  (PR [#4186](https://github.com/pipecat-ai/pipecat/pull/4186))
-
-### Performance
-
-- `RimeTTSService` now handles Rime's `done` WebSocket message to complete
-  audio contexts immediately, eliminating the 3-second idle timeout that
-  previously added latency at the end of each utterance.
-  (PR [#4172](https://github.com/pipecat-ai/pipecat/pull/4172))
-
-## [0.0.107] - 2026-03-23
-
-### Added
-
-- Added `frame_order` parameter to `SyncParallelPipeline`. Set
-  `frame_order=FrameOrder.PIPELINE` to push synchronized output frames in
-  pipeline definition order (all frames from the first pipeline, then the
-  second, etc.) instead of the default arrival order.
-  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
-
-- Added `sync_with_audio` field to `OutputImageRawFrame`. When set to `True`,
-  the output transport queues image frames with audio so they are displayed
-  only after all preceding audio has been sent, enabling synchronized
-  audio/image playback.
-  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
-
-- Added `OpenAIResponsesLLMService`, a new LLM service that uses the OpenAI
-  Responses API. Supports streaming text, function calling, usage metrics, and
-  out-of-band inference. Works with the universal `LLMContext` and
-  `LLMContextAggregatorPair`. See
-  `examples/foundational/07-interruptible-openai-responses.py` and
-  `14-function-calling-openai-responses.py`.
-  (PR [#4074](https://github.com/pipecat-ai/pipecat/pull/4074))
-
-- Added `audio_out_auto_silence` parameter to `TransportParams` (defaults to
-  `True`). When set to `False`, the transport waits for audio data instead of
-  inserting silence when the output queue is empty, which is useful for
-  scenarios that require uninterrupted audio playback without artificial gaps.
-  (PR [#4104](https://github.com/pipecat-ai/pipecat/pull/4104))
-
-### Changed
-
-- Renamed tracing span attributes to align with OpenTelemetry GenAI semantic
-  conventions: `gen_ai.system` to `gen_ai.provider.name`, `system` to
-  `gen_ai.system_instructions`, `gen_ai.usage.cache_read_input_tokens` to
-  `gen_ai.usage.cache_read.input_tokens`, and
-  `gen_ai.usage.cache_creation_input_tokens` to
-  `gen_ai.usage.cache_creation.input_tokens`.
-  (PR [#3449](https://github.com/pipecat-ai/pipecat/pull/3449))
-
-- `DeepgramSageMakerTTSService` now correctly routes audio through the base
-  `TTSService` audio context queue. Audio frames are delivered via
-  `append_to_audio_context()` instead of being pushed directly, enabling proper
-  ordering, interruption handling, and start/stop frame lifecycle management.
-  Interruptions now trigger a `Clear` message to Deepgram (flushing its text
-  buffer) at the right time via `on_audio_context_interrupted`.
-  (PR [#4083](https://github.com/pipecat-ai/pipecat/pull/4083))
-
-- `GradiumTTSService` now sends a per-context `setup` message with
-  `client_req_id` before the first text message for each TTS context, following
-  Gradium's multiplexing protocol. Previously, a single setup message was sent
-  at connection time without a `client_req_id`, which prevented Gradium from
-  associating requests with their sessions when using `close_ws_on_eos=False`.
-  (PR [#4091](https://github.com/pipecat-ai/pipecat/pull/4091))
-
-### Fixed
-
-- Fixed stale `system_instruction` in LLM tracing spans by reading from
-  `_settings.system_instruction` instead of the removed `_system_instruction`
-  attribute.
-  (PR [#3449](https://github.com/pipecat-ai/pipecat/pull/3449))
-
-- Fixed `SyncParallelPipeline` breaking the Whisker debugger.
-  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
-
-- Fixed `SyncParallelPipeline` race condition where concurrent SystemFrame
-  processing (e.g. from RTVI) could corrupt sink queues and cause deadlocks.
-  SystemFrames now take a fast path that passes them through without draining
-  queued output.
-  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
-
-- Fixed TTS frame ordering so that non-system frames always arrive in correct
-  order relative to the `TTSStartedFrame`/`TTSAudioRawFrame`/`TTSStoppedFrame`
-  sequence. Previously these frames could race ahead of or behind audio context
-  frames, producing out-of-order output downstream.
-  (PR [#4075](https://github.com/pipecat-ai/pipecat/pull/4075))
-
-- Fixed `SarvamTTSService` audio and error frames now route through
-  `append_to_audio_context()` instead of `push_frame()`, ensuring correct
-  behavior with audio contexts and interruptions.
-  (PR [#4082](https://github.com/pipecat-ai/pipecat/pull/4082))
-
-- Fixed audio frame ordering and interruption handling in Fish Audio, LMNT,
-  Neuphonic, and Rime NonJson TTS services. These services were bypassing the
-  base `TTSService` audio context serialization queue by pushing audio frames
-  directly, which could cause out-of-order frames and broken interruptions
-  during speech.
-  (PR [#4090](https://github.com/pipecat-ai/pipecat/pull/4090))
-
-- Fixed Genesys AudioHook serializer to always include the `parameters` field in
-  protocol messages. The AudioHook protocol requires every message to carry a
-  `parameters` object (even if empty), but `_create_message` omitted it when no
-  parameters were provided. This caused clients that validate message structure
-  (including the Genesys reference implementation) to reject `pong` and
-  parameter-less `closed` responses, breaking server sequence tracking and
-  preventing `outputVariables` from reaching the Architect flow.
-  (PR [#4093](https://github.com/pipecat-ai/pipecat/pull/4093))
-
-## [0.0.106] - 2026-03-18
-
-### Added
-
-- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its
-  subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`,
-  `STTUpdateSettingsFrame`) to target a specific service instance. When
-  `service` is set, only the matching service applies the settings; others
-  forward the frame unchanged. This enables updating a single service when
-  multiple services of the same type exist in the pipeline.
-  (PR [#4004](https://github.com/pipecat-ai/pipecat/pull/4004))
-
-- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily
-  runner. These convenience parameters let callers specify a SIP provider name
-  and geographic region directly without manually constructing
-  `DailyRoomProperties` and `DailyRoomSipParams`.
-  (PR [#4005](https://github.com/pipecat-ai/pipecat/pull/4005))
-
-- Added `PerplexityLLMAdapter` that automatically transforms conversation
-  messages to satisfy Perplexity's stricter API constraints (strict role
-  alternation, no non-initial system messages, last message must be user/tool).
-  Previously, certain conversation histories could cause Perplexity API errors
-  that didn't occur with OpenAI (`PerplexityLLMService` subclasses
-  `OpenAILLMService` since Perplexity uses an OpenAI-compatible API).
-  (PR [#4009](https://github.com/pipecat-ai/pipecat/pull/4009))
-
-- Added DTMF input event support to the Daily transport. Incoming DTMF tones
-  are now received via Daily's `on_dtmf_event` callback and pushed into the
-  pipeline as `InputDTMFFrame`, enabling bots to react to keypad presses from
-  phone callers.
-  (PR [#4047](https://github.com/pipecat-ai/pipecat/pull/4047))
-
-- Added `WakePhraseUserTurnStartStrategy` for triggering user turns based on
-  wake phrases, with support for `single_activation` mode. Deprecates
-  `WakeCheckFilter`.
-  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
-
-- Added `default_user_turn_start_strategies()` and
-  `default_user_turn_stop_strategies()` helper functions for composing custom
-  strategy lists.
-  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
-
-### Changed
-
-- Changed tool result JSON serialization to use `ensure_ascii=False`,
-  preserving UTF-8 characters instead of escaping them. This reduces context
-  size and token usage for non-English languages.
-  (PR [#3457](https://github.com/pipecat-ai/pipecat/pull/3457))
-
-- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of
-  `OpenAIRealtimeSTTSettings`, making it runtime-updatable via
-  `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is
-  deprecated as of 0.0.106.
-  (PR [#3991](https://github.com/pipecat-ai/pipecat/pull/3991))
-
-- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable
-  release).
-  (PR [#3997](https://github.com/pipecat-ai/pipecat/pull/3997))
-
-- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`,
-  aligning it with the HeyGen and Tavus video services. It supports
-  `SimliVideoService.Settings(...)` for configuration and uses
-  `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage
-  (`api_key`, `face_id`, etc.) remains unchanged.
-  (PR [#4001](https://github.com/pipecat-ai/pipecat/pull/4001))
-
-- Update `pipecat-ai-small-webrtc-prebuilt` to `2.4.0`.
-  (PR [#4023](https://github.com/pipecat-ai/pipecat/pull/4023))
-
-- Nova Sonic assistant text transcripts are now delivered in real-time using
-  speculative text events instead of delayed final text events. Previously,
-  assistant text only arrived after all audio had finished playing, causing
-  laggy transcripts in client UIs. Speculative text arrives before each audio
-  chunk, providing text synchronized with what the bot is saying. This also
-  simplifies the internal text handling by removing the interruption re-push
-  hack and assistant text buffer.
-  (PR [#4042](https://github.com/pipecat-ai/pipecat/pull/4042))
-
-- Updated `daily-python` dependency to 0.25.0.
-  (PR [#4047](https://github.com/pipecat-ai/pipecat/pull/4047))
-
-- Added `enable_dialout` parameter to `configure()` in `pipecat.runner.daily`
-  to support dial-out rooms. Also narrowed misleading `Optional` type hints and
-  deduplicated token expiry calculation.
-  (PR [#4048](https://github.com/pipecat-ai/pipecat/pull/4048))
-
-- Extended `ProcessFrameResult` to stop strategies, allowing a stop strategy to
-  short-circuit evaluation of subsequent strategies by returning `STOP`.
-  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
-
-- `GradiumSTTService` now takes both an `encoding` and `sample_rate`
-  constructor argument which is assmebled in the class to form the
-  `input_format`. PCM accepts `8000`, `16000`, and `24000` Hz sample rates.
-  (PR [#4066](https://github.com/pipecat-ai/pipecat/pull/4066))
-
-- Improved `GradiumSTTService` transcription accuracy by reworking how text
-  fragments are accumulated and finalized. Previously, trailing words could be
-  dropped when the server's `flushed` response arrived before all text tokens
-  were delivered. The service now uses a short aggregation delay after flush to
-  capture trailing tokens, producing complete utterances.
-  (PR [#4066](https://github.com/pipecat-ai/pipecat/pull/4066))
-
-### Deprecated
-
-- `SimliVideoService.InputParams` is deprecated. Use the direct constructor
-  parameters `max_session_length`, `max_idle_time`, and `enable_logging`
-  instead.
-  (PR [#4001](https://github.com/pipecat-ai/pipecat/pull/4001))
-
-- Deprecated `LocalSmartTurnAnalyzerV2` and `LocalCoreMLSmartTurnAnalyzer`. Use
-  `LocalSmartTurnAnalyzerV3` instead. Instantiating these analyzers will now
-  emit a `DeprecationWarning`.
-  (PR [#4012](https://github.com/pipecat-ai/pipecat/pull/4012))
-
-- Deprecated `WakeCheckFilter` in favor of `WakePhraseUserTurnStartStrategy`.
-  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
-
-### Fixed
-
-- Fixed an issue where the default model for `OpenAILLMService` and
-  `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now
-  restored to `gpt-4.1`.
-  (PR [#4000](https://github.com/pipecat-ai/pipecat/pull/4000))
-
-- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut
-  down before in-flight frames (e.g. LLM function call responses) finished
-  processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline
-  as `ControlFrame`s, ensuring all pending work is flushed before shutdown
-  begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate
-  (`SystemFrame`).
-  (PR [#4006](https://github.com/pipecat-ai/pipecat/pull/4006))
-
-- Fixed `ParallelPipeline` dropping or misordering frames during lifecycle
-  synchronization. Buffered frames are now flushed in the correct order
-  relative to synchronization frames (`StartFrame` goes first,
-  `EndFrame`/`CancelFrame` go after), and frames added to the buffer during
-  flush are also drained.
-  (PR [#4007](https://github.com/pipecat-ai/pipecat/pull/4007))
-
-- Fixed `TTSService` potentially canceling in-flight audio during shutdown. The
-  stop sequence now waits for all queued audio contexts to finish processing
-  before canceling the stop frame task.
-  (PR [#4007](https://github.com/pipecat-ai/pipecat/pull/4007))
-
-- Fixed `Language` enum values (e.g. `Language.ES`) not being converted to
-  service-specific codes when passed via
-  `settings=Service.Settings(language=Language.ES)` at init time. This caused
-  API errors (e.g. 400 from Rime) because the raw enum was sent instead of the
-  expected language code (e.g. `"spa"`). Runtime updates via
-  `UpdateSettingsFrame` were unaffected. The fix centralizes conversion in the
-  base `TTSService` and `STTService` classes so all services handle this
-  consistently.
-  (PR [#4024](https://github.com/pipecat-ai/pipecat/pull/4024))
-
-- Fixed `DeepgramSTTService` ignoring the `base_url` scheme when using `ws://`
-  or `http://`. Previously these were silently overwritten with `wss://` /
-  `https://`, breaking air-gapped or private deployments that don't use TLS.
-  All scheme choices (`wss://`, `https://`, `ws://`, `http://`, or bare
-  hostname) are now respected.
-  (PR [#4026](https://github.com/pipecat-ai/pipecat/pull/4026))
-
-- Fixed `LLMSwitcher.register_function()` and `register_direct_function()` not
-  accepting or forwarding the `timeout_secs` parameter.
-  (PR [#4037](https://github.com/pipecat-ai/pipecat/pull/4037))
-
-- Fixed empty user transcriptions in Nova Sonic causing spurious interruptions.
-  Previously, an empty transcription could trigger an interruption of the
-  assistant's response even though the user hadn't actually spoken.
-  (PR [#4042](https://github.com/pipecat-ai/pipecat/pull/4042))
-
-- Fixed `SonioxSTTService` and `OpenAIRealtimeSTTService` crash when language
-  parameters contain plain strings instead of `Language` enum values.
-  (PR [#4046](https://github.com/pipecat-ai/pipecat/pull/4046))
-
-- Fixed premature user turn stops caused by late transcriptions arriving
-  between turns. A stale transcript from the previous turn could persist into
-  the next turn and trigger a stop before the current turn's real transcript
-  arrived. Stop strategies are now reset at both turn start and turn stop to
-  prevent state from leaking across turn boundaries.
-  (PR [#4057](https://github.com/pipecat-ai/pipecat/pull/4057))
-
-- Fixed raw language strings like `"de-DE"` silently failing when passed to
-  TTS/STT services (e.g. ElevenLabs producing no audio). Raw strings now go
-  through the same `Language` enum resolution as enum values, so regional codes
-  like `"de-DE"` are properly converted to service-expected formats like
-  `"de"`. Unrecognized strings log a warning instead of failing silently.
-  (PR [#4058](https://github.com/pipecat-ai/pipecat/pull/4058))
-
-- Fixed Deepgram STT list-type settings (`keyterm`, `keywords`, `search`,
-  `redact`, `replace`) being stringified instead of passed as lists to the SDK,
-  which caused them to be sent as literal strings (e.g. `"['pipecat']"`) in the
-  WebSocket query params.
-  (PR [#4063](https://github.com/pipecat-ai/pipecat/pull/4063))
-
-- Fixed `MinWordsUserTurnStartStrategy` including text below the word threshold
-  in the output by resetting aggregation when the minimum word count is not
-  met.
-  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
-
-- Fixed audio overlap and potential dropped TTS content when multiple assistant
-  turns occur in quick succession. `TTSService` now flushes remaining text
-  before pausing frame processing on `LLMFullResponseEndFrame`/`EndFrame`,
-  instead of pausing first.
-  (PR [#4071](https://github.com/pipecat-ai/pipecat/pull/4071))
-
-### Security
-
-- Bumped PyJWT minimum version from 2.10.1 to 2.12.0 in the `livekit` extra to
-  address CVE-2026-32597 (GHSA-752w-5fwx-jx9f), where PyJWT <= 2.11.0 accepted
-  unknown `crit` header extensions.
-  (PR [#4035](https://github.com/pipecat-ai/pipecat/pull/4035))
-
 ## [0.0.105] - 2026-03-10
 
 ### Added

CLAUDE.md

@@ -10,7 +10,7 @@ Pipecat is an open-source Python framework for building real-time voice and mult
 
 ```bash
 # Setup development environment
-uv sync --group dev --all-extras --no-extra gstreamer
+uv sync --group dev --all-extras --no-extra gstreamer --no-extra krisp
 
 # Install pre-commit hooks
 uv run pre-commit install

COMMUNITY_INTEGRATIONS.md

@@ -23,7 +23,7 @@ Create your integration following the patterns and examples shown in the "Integr
 Your repository must contain these components:
 
 - **Source code** - Complete implementation following Pipecat patterns
-- **Foundational example** - Single file example showing basic usage (see [Pipecat examples](https://github.com/pipecat-ai/pipecat/tree/main/examples))
+- **Foundational example** - Single file example showing basic usage (see [Pipecat examples](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational))
 - **README.md** - Must include:
   - Introduction and explanation of your integration
   - Installation instructions
@@ -65,25 +65,12 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 #### Websocket-based Services
 
-**Base class:** `WebsocketSTTService`
-
-**Use for:** Services where you manage the websocket connection directly. Combines `STTService` with `WebsocketService` for automatic reconnection and keepalive support.
-
-**Examples:**
-
-- [CartesiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/stt.py)
-- [ElevenLabsRealtimeSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/stt.py)
-
-#### SDK-based Streaming Services
-
 **Base class:** `STTService`
 
-**Use for:** Streaming services where the provider's Python SDK manages the connection internally.
-
 **Examples:**
 
 - [DeepgramSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/deepgram/stt.py)
-- [GoogleSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/stt.py)
+- [SpeechmaticsSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/speechmatics/stt.py)
 
 #### File-based Services
 
@@ -121,59 +108,55 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 #### Key requirements:
 
-- **`_process_context(self, context: LLMContext)`** — The main method that processes an LLM context and generates a response. Each LLM service overrides `process_frame` to extract context from `LLMContextFrame` and calls `_process_context`.
-
-- **`adapter_class`** — Class attribute pointing to a `BaseLLMAdapter` subclass. Defaults to `OpenAILLMAdapter`. Non-OpenAI services must implement their own adapter (see `src/pipecat/adapters/base_llm_adapter.py`) with methods:
-  - `get_llm_invocation_params(context)` — Extract provider-specific params from universal context
-  - `to_provider_tools_format(tools_schema)` — Convert standard tools to provider format
-  - `get_messages_for_logging(context)` — Format messages for logging
-  - Reference adapters: `src/pipecat/adapters/services/` (anthropic, gemini, bedrock, etc.)
-
 - **Frame sequence:** Output must follow this frame sequence pattern:
-  - `LLMFullResponseStartFrame` — Signals the start of an LLM response
-  - `LLMTextFrame` — Contains LLM content, typically streamed as tokens
-  - `LLMFullResponseEndFrame` — Signals the end of an LLM response
+  - `LLMFullResponseStartFrame` - Signals the start of an LLM response
+  - `LLMTextFrame` - Contains LLM content, typically streamed as tokens
+  - `LLMFullResponseEndFrame` - Signals the end of an LLM response
 
-- **Thought frames (reasoning models):** If the model supports extended thinking / chain-of-thought, emit thought frames alongside the response:
-  - `LLMThoughtStartFrame` — Signals the start of a thought
-  - `LLMThoughtTextFrame` — Contains thought content, streamed as tokens
-  - `LLMThoughtEndFrame` — Signals the end of a thought
-
-- **Context aggregation** is handled by the framework via `LLMContext` + `LLMContextAggregatorPair`. The LLM service just processes context it receives — no need to implement aggregators.
+- **Context aggregation:** Implement context aggregation to collect user and assistant content:
+  - Aggregators come in pairs with a `user()` instance and `assistant()` instance
+  - Context must adhere to the `LLMContext` universal format
+  - Aggregators should handle adding messages, function calls, and images to the context
 
 ### TTS (Text-to-Speech) Services
 
-#### WebsocketTTSService
+#### AudioContextWordTTSService
 
-**Use for:** Websocket-based streaming services (with or without word timestamps)
+**Use for:** Websocket-based services supporting word/timestamp alignment
 
-**Examples:**
+**Example:**
 
 - [CartesiaTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/tts.py)
-- [ElevenLabsTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
 
 #### InterruptibleTTSService
 
-**Use for:** Websocket-based services without word timestamps that reconnect on interruption (e.g. don't support a context ID or interruption message)
+**Use for:** Websocket-based services without word/timestamp alignment, requiring disconnection on interruption
 
 **Example:**
 
 - [SarvamTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/sarvam/tts.py)
 
+#### WordTTSService
+
+**Use for:** HTTP-based services supporting word/timestamp alignment
+
+**Example:**
+
+- [ElevenLabsHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
+
 #### TTSService
 
-**Use for:** HTTP-based services (word timestamps are supported in the base class)
+**Use for:** HTTP-based services without word/timestamp alignment
 
-**Examples:**
+**Example:**
 
 - [GoogleHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/tts.py)
-- [OpenAITTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/openai/tts.py)
 
 #### Key requirements:
 
-- For websocket services, use asyncio WebSocket implementation
+- For websocket services, use asyncio WebSocket implementation (required for v13+ support)
 - Handle idle service timeouts with keepalives
-- TTS services push both audio (`TTSAudioRawFrame`) and text (`TTSTextFrame`) frames
+- TTSServices push both audio (`TTSRawAudioFrame`) and text (`TTSTextFrame`) frames
 
 ### Telephony Serializers
 
@@ -217,25 +200,14 @@ Vision services process images and provide analysis such as descriptions, object
 
 #### Key requirements:
 
-- Must implement `run_vision` method that takes a `UserImageRawFrame` and returns an `AsyncGenerator[Frame, None]`
-- The method processes the image frame and yields frames with analysis results
-- Must yield the frame sequence: `VisionFullResponseStartFrame`, `VisionTextFrame`, `VisionFullResponseEndFrame`
+- Must implement `run_vision` method that takes an `LLMContext` and returns an `AsyncGenerator[Frame, None]`
+- The method processes the latest image in the context and yields frames with analysis results
+- Typically yields `TextFrame` objects containing descriptions or answers
 
 ## Implementation Guidelines
 
 ### Naming Conventions
 
-#### Package and Repository Naming
-
-Use the `pipecat-{vendor}` naming convention for your PyPI package and repository:
-
-- `pipecat-{vendor}` — for single-service integrations (e.g., `pipecat-deepdub`)
-- `pipecat-{vendor}-{type}` — when a vendor offers multiple service types (e.g., `pipecat-upliftai-stt`, `pipecat-upliftai-tts`)
-
-This convention makes community packages easily discoverable via PyPI search and clearly identifies them as part of the Pipecat ecosystem.
-
-#### Class Naming
-
 - **STT:** `VendorSTTService`
 - **LLM:** `VendorLLMService`
 - **TTS:**
@@ -409,7 +381,7 @@ Note that `self.sample_rate` is a `@property` set in the TTSService base class,
 
 Use Pipecat's tracing decorators:
 
-- **STT:** `@traced_stt` - decorate `_handle_transcription(self, transcript, is_final, language)` (the standard method name convention)
+- **STT:** `@traced_stt` - decorate a function that handles `transcript`, `is_final`, `language` as args
 - **LLM:** `@traced_llm` - decorate the `_process_context()` method
 - **TTS:** `@traced_tts` - decorate the `run_tts()` method
 
@@ -417,9 +389,8 @@ Use Pipecat's tracing decorators:
 
 ### Packaging and Distribution
 
-- Name your package `pipecat-{vendor}` (see [Naming Conventions](#naming-conventions))
 - Use [uv](https://docs.astral.sh/uv/) for packaging (encouraged)
-- Publish to PyPI for easier installation
+- Consider releasing to PyPI for easier installation
 - Follow semantic versioning principles
 - Maintain a changelog
 
@@ -432,15 +403,17 @@ For REST-based communication, use aiohttp. Pipecat includes this as a required d
 - Wrap API calls in appropriate try/catch blocks
 - Handle rate limits and network failures gracefully
 - Provide meaningful error messages
-- When errors occur, raise exceptions AND push errors to notify the pipeline:
+- When errors occur, raise exceptions AND push `ErrorFrame`s to notify the pipeline:
 
 ```python
+from pipecat.frames.frames import ErrorFrame
+
 try:
     # Your API call
     result = await self._make_api_call()
 except Exception as e:
-    # Push error upstream to notify the pipeline
-    await self.push_error(f"{self} error: {e}", exception=e)
+    # Push error frame to pipeline
+    await self.push_error(ErrorFrame(error=f"{self} error: {e}"))
     # Raise or handle as appropriate
     raise
 ```

README.md

@@ -8,7 +8,7 @@
 
 **Pipecat** is an open-source Python framework for building real-time voice and multimodal conversational agents. Orchestrate audio and video, AI services, different transports, and conversation pipelines effortlessly—so you can focus on what makes your agent unique.
 
-> Want to dive right in? Run `pipecat init quickstart` or follow the [quickstart guide](https://docs.pipecat.ai/getting-started/quickstart).
+> Want to dive right in? Try the [quickstart](https://docs.pipecat.ai/getting-started/quickstart).
 
 ## 🚀 What You Can Build
 
@@ -65,10 +65,6 @@ claude plugin marketplace add pipecat-ai/skills
 
 and install any of the available plugins.
 
-### 🧩 Community Integrations
-
-Build and share your own Pipecat service integrations! Browse existing [community integrations](https://docs.pipecat.ai/server/services/community-integrations) or check out our [guide](COMMUNITY_INTEGRATIONS.md) to create your own.
-
 ### 📺️ Pipecat TV Channel
 
 Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
@@ -80,25 +76,24 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
     <br/>
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>&nbsp;
-    <a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/vision/vision-moondream.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/assets/moondream.png" width="400" /></a>
+    <a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.png" width="400" /></a>
 </p>
 
 ## 🧩 Available services
 
-| 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), [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), [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), [Nebius](https://docs.pipecat.ai/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [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), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [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), [Kokoro](https://docs.pipecat.ai/server/services/tts/kokoro), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox),                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [LiveKit (WebRTC)](https://docs.pipecat.ai/server/services/transport/livekit), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), [WhatsApp](https://docs.pipecat.ai/server/services/transport/whatsapp), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-| Serializers         | [Exotel](https://docs.pipecat.ai/server/services/serializers/exotel), [Genesys](https://docs.pipecat.ai/server/services/serializers/genesys), [Plivo](https://docs.pipecat.ai/server/services/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/services/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/services/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/services/serializers/vonage)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/transport/lemonslice), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp Viva](https://docs.pipecat.ai/guides/features/krisp-viva), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter), [RNNoise](https://docs.pipecat.ai/server/utilities/audio/rnnoise-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| Community           | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| 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), [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), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/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         | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [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), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -142,7 +137,7 @@ You can get started with Pipecat running on your local machine, then move your a
 
 ## 🧪 Code examples
 
-- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples) — small snippets that build on each other, introducing one or two concepts at a time
+- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
 - [Example apps](https://github.com/pipecat-ai/pipecat-examples) — complete applications that you can use as starting points for development
 
 ## 🛠️ Contributing to the framework
@@ -166,6 +161,7 @@ You can get started with Pipecat running on your local machine, then move your a
    ```bash
    uv sync --group dev --all-extras \
      --no-extra gstreamer \
+     --no-extra krisp \
      --no-extra local \
    ```
 

changelog/3457.changed.md

@@ -0,0 +1 @@
+- Changed tool result JSON serialization to use `ensure_ascii=False`, preserving UTF-8 characters instead of escaping them. This reduces context size and token usage for non-English languages.

changelog/3991.changed.md

@@ -0,0 +1 @@
+- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of `OpenAIRealtimeSTTSettings`, making it runtime-updatable via `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is deprecated as of 0.0.106.

changelog/3997.changed.md

@@ -0,0 +1 @@
+- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable release).

changelog/4000.fixed.md

@@ -0,0 +1 @@
+- Fixed an issue where the default model for `OpenAILLMService` and `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now restored to `gpt-4.1`.

changelog/4001.changed.md

@@ -0,0 +1 @@
+- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`, aligning it with the HeyGen and Tavus video services. It supports `SimliVideoService.Settings(...)` for configuration and uses `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage (`api_key`, `face_id`, etc.) remains unchanged.

changelog/4001.deprecated.md

@@ -0,0 +1 @@
+- `SimliVideoService.InputParams` is deprecated. Use the direct constructor parameters `max_session_length`, `max_idle_time`, and `enable_logging` instead.

changelog/4004.added.md

@@ -0,0 +1 @@
+- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `STTUpdateSettingsFrame`) to target a specific service instance. When `service` is set, only the matching service applies the settings; others forward the frame unchanged. This enables updating a single service when multiple services of the same type exist in the pipeline.

changelog/4005.added.md

@@ -0,0 +1 @@
+- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily runner. These convenience parameters let callers specify a SIP provider name and geographic region directly without manually constructing `DailyRoomProperties` and `DailyRoomSipParams`.

changelog/4006.fixed.md

@@ -0,0 +1 @@
+- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut down before in-flight frames (e.g. LLM function call responses) finished processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline as `ControlFrame`s, ensuring all pending work is flushed before shutdown begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate (`SystemFrame`).

changelog/4007.fixed.2.md

@@ -0,0 +1 @@
+- Fixed `TTSService` potentially canceling in-flight audio during shutdown. The stop sequence now waits for all queued audio contexts to finish processing before canceling the stop frame task.

changelog/4007.fixed.md

@@ -0,0 +1 @@
+- Fixed `ParallelPipeline` dropping or misordering frames during lifecycle synchronization. Buffered frames are now flushed in the correct order relative to synchronization frames (`StartFrame` goes first, `EndFrame`/`CancelFrame` go after), and frames added to the buffer during flush are also drained.

changelog/4009.added.md

@@ -0,0 +1 @@
+- Added `PerplexityLLMAdapter` that automatically transforms conversation messages to satisfy Perplexity's stricter API constraints (strict role alternation, no non-initial system messages, last message must be user/tool). Previously, certain conversation histories could cause Perplexity API errors that didn't occur with OpenAI (`PerplexityLLMService` subclasses `OpenAILLMService` since Perplexity uses an OpenAI-compatible API).

changelog/4012.deprecated.md

@@ -0,0 +1 @@
+- Deprecated `LocalSmartTurnAnalyzerV2` and `LocalCoreMLSmartTurnAnalyzer`. Use `LocalSmartTurnAnalyzerV3` instead. Instantiating these analyzers will now emit a `DeprecationWarning`.

changelog/4023.changed.md

@@ -0,0 +1 @@
+- Update `pipecat-ai-small-webrtc-prebuilt` to `2.4.0`.

changelog/4024.fixed.md

@@ -0,0 +1 @@
+- Fixed `Language` enum values (e.g. `Language.ES`) not being converted to service-specific codes when passed via `settings=Service.Settings(language=Language.ES)` at init time. This caused API errors (e.g. 400 from Rime) because the raw enum was sent instead of the expected language code (e.g. `"spa"`). Runtime updates via `UpdateSettingsFrame` were unaffected. The fix centralizes conversion in the base `TTSService` and `STTService` classes so all services handle this consistently.

changelog/4026.fixed.md

@@ -0,0 +1 @@
+- Fixed `DeepgramSTTService` ignoring the `base_url` scheme when using `ws://` or `http://`. Previously these were silently overwritten with `wss://` / `https://`, breaking air-gapped or private deployments that don't use TLS. All scheme choices (`wss://`, `https://`, `ws://`, `http://`, or bare hostname) are now respected.

changelog/4035.security.md

@@ -0,0 +1 @@
+- Bumped PyJWT minimum version from 2.10.1 to 2.12.0 in the `livekit` extra to address CVE-2026-32597 (GHSA-752w-5fwx-jx9f), where PyJWT <= 2.11.0 accepted unknown `crit` header extensions.

changelog/4037.fixed.md

@@ -0,0 +1 @@
+- Fixed `LLMSwitcher.register_function()` and `register_direct_function()` not accepting or forwarding the `timeout_secs` parameter.

changelog/4046.fixed.md

@@ -0,0 +1 @@
+Fixed `SonioxSTTService` and `OpenAIRealtimeSTTService` crash when language parameters contain plain strings instead of `Language` enum values.

changelog/4047.added.md

@@ -0,0 +1 @@
+- Added DTMF input event support to the Daily transport. Incoming DTMF tones are now received via Daily's `on_dtmf_event` callback and pushed into the pipeline as `InputDTMFFrame`, enabling bots to react to keypad presses from phone callers.

changelog/4047.changed.md

@@ -0,0 +1 @@
+- Updated `daily-python` dependency to 0.25.0.

changelog/4048.changed.md

@@ -0,0 +1 @@
+- Added `enable_dialout` parameter to `configure()` in `pipecat.runner.daily` to support dial-out rooms. Also narrowed misleading `Optional` type hints and deduplicated token expiry calculation.

changelog/4057.fixed.md

@@ -0,0 +1 @@
+- Fixed premature user turn stops caused by late transcriptions arriving between turns. A stale transcript from the previous turn could persist into the next turn and trigger a stop before the current turn's real transcript arrived. Stop strategies are now reset at both turn start and turn stop to prevent state from leaking across turn boundaries.

changelog/4058.fixed.md

@@ -0,0 +1 @@
+- Fixed raw language strings like `"de-DE"` silently failing when passed to TTS/STT services (e.g. ElevenLabs producing no audio). Raw strings now go through the same `Language` enum resolution as enum values, so regional codes like `"de-DE"` are properly converted to service-expected formats like `"de"`. Unrecognized strings log a warning instead of failing silently.

changelog/4063.fixed.md

@@ -0,0 +1 @@
+- Fixed Deepgram STT list-type settings (`keyterm`, `keywords`, `search`, `redact`, `replace`) being stringified instead of passed as lists to the SDK, which caused them to be sent as literal strings (e.g. `"['pipecat']"`) in the WebSocket query params.

changelog/4141.added.md

@@ -1 +0,0 @@
-- ⚠️ Added WebSocket-based `OpenAIResponsesLLMService` as the new default for the OpenAI Responses API. It maintains a persistent connection to `wss://api.openai.com/v1/responses` and automatically uses `previous_response_id` to send only incremental context, falling back to full context on reconnection or cache miss. The previous HTTP-based implementation is now available as `OpenAIResponsesHttpLLMService`.

changelog/4191.removed.md

@@ -1 +0,0 @@
-- ⚠️ Removed `OpenPipeLLMService` and the `openpipe` extra. OpenPipe was acquired by CoreWeave and the package is no longer maintained. If you were using `openpipe` as an LLM provider, switch to the underlying provider directly (e.g. `openai`). The OpenPipe interface can still be used with `OpenAILLMService` by specifying a `base_url`.

changelog/4192.changed.md

@@ -1 +0,0 @@
-- ⚠️ Updated `langchain` extra to require langchain 1.x (from 0.3.x), langchain-community 0.4.x (from 0.3.x), and langchain-openai 1.x (from 0.3.x). If you pin these packages in your project, update your pins accordingly.

changelog/4202.fixed.md

@@ -1 +0,0 @@
-- Fixed `InworldHttpTTSService` streaming responses crashing with `UnicodeDecodeError` when multi-byte UTF-8 characters were split across chunk boundaries. This caused TTS audio to cut off mid-sentence intermittently.

changelog/4203.fixed.md

@@ -1 +0,0 @@
-- Fixed a crash (`JSONDecodeError`) when a user interruption occurs while the LLM is streaming function call arguments. Previously, the incomplete JSON arguments were passed directly to `json.loads()`, causing an unhandled exception. Affected services: OpenAI, Google (OpenAI-compatible), and SambaNova.

changelog/4204.removed.10.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `observers` field from `PipelineParams`. Pass observers directly to `PipelineTask` constructor instead.

changelog/4204.removed.11.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `on_pipeline_ended`, `on_pipeline_cancelled`, and `on_pipeline_stopped` events from `PipelineTask`. Use `on_pipeline_finished` instead.

changelog/4204.removed.12.md

@@ -1 +0,0 @@
-- ⚠️ Removed `AudioBufferProcessor.user_continuous_stream` parameter. Use `user_audio_passthrough` instead.

changelog/4204.removed.13.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `camera_in_enabled`, `camera_in_is_live`, `camera_in_width`, `camera_in_height`, `camera_out_enabled`, `camera_out_is_live`, `camera_out_width`, `camera_out_height`, and `camera_out_color` transport params. Use the `video_in_*` and `video_out_*` equivalents instead.

changelog/4204.removed.14.md

@@ -1 +0,0 @@
-- ⚠️ Removed `RTVIObserver.errors_enabled` parameter.

changelog/4204.removed.15.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `vad_enabled` and `vad_audio_passthrough` transport params.

changelog/4204.removed.16.md

@@ -1 +0,0 @@
-- ⚠️ Removed `TTSService.say()`. Push a `TTSSpeakFrame` into the pipeline instead.

changelog/4204.removed.17.md

@@ -1 +0,0 @@
-- ⚠️ Removed `DailyRunner.configure_with_args()`. Use `PipelineRunner` with `RunnerArguments` instead.

changelog/4204.removed.18.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated RTVI models, frames, and processor methods including `RTVIConfig`, `RTVIServiceConfig`, `RTVIServiceOptionConfig`, various `RTVI*Data` models, `RTVIActionFrame`, and `RTVIProcessor.handle_function_call`/`handle_function_call_start`. Use the updated RTVI processor API instead.

changelog/4204.removed.19.md

@@ -1 +0,0 @@
-- ⚠️ Removed `FrameProcessor.wait_for_task()`. Use `create_task()` and manage tasks with the built-in `TaskManager` instead.

changelog/4204.removed.2.md

@@ -1 +0,0 @@
-- ⚠️ Removed `KrispFilter`. The `krisp` extra has been removed from `pyproject.toml`.

changelog/4204.removed.20.md

@@ -1 +0,0 @@
-- ⚠️ Removed `LLMService.request_image_frame()`. Push a `UserImageRequestFrame` instead.

changelog/4204.removed.3.md

@@ -1 +0,0 @@
-- ⚠️ Removed `create_default_resampler()` from `pipecat.audio.utils`.

changelog/4204.removed.4.md

@@ -1 +0,0 @@
-- ⚠️ Removed `FalSmartTurnAnalyzer` and `LocalSmartTurnAnalyzer`.

changelog/4204.removed.5.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated transport frames: `TransportMessageFrame`, `TransportMessageUrgentFrame`, `InputTransportMessageUrgentFrame`, `DailyTransportMessageFrame`, and `DailyTransportMessageUrgentFrame`. Use `OutputTransportMessageFrame`, `OutputTransportMessageUrgentFrame`, `InputTransportMessageFrame`, `DailyOutputTransportMessageFrame`, and `DailyOutputTransportMessageUrgentFrame` instead.

changelog/4204.removed.6.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `KeypadEntryFrame` alias.

changelog/4204.removed.7.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated interruption frames: `StartInterruptionFrame` and `BotInterruptionFrame`. Use `InterruptionFrame` and `InterruptionTaskFrame` instead.

changelog/4204.removed.8.md

@@ -1 +0,0 @@
-- ⚠️ Removed `LLMService.start_callback` parameter. Register an `on_llm_response_start` event handler instead.

changelog/4204.removed.9.md

@@ -1 +0,0 @@
-- ⚠️ Removed single-argument function call support from `LLMService`. Functions must use named parameters instead of a single `arguments` parameter.

changelog/4204.removed.md

@@ -1 +0,0 @@
-- ⚠️ Removed `NoisereduceFilter`. Use system-level noise reduction or a service-based alternative instead.

changelog/4208.removed.10.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.riva` package. Use `pipecat.services.nvidia.stt` and `pipecat.services.nvidia.tts` instead (`RivaSTTService` → `NvidiaSTTService`, `RivaTTSService` → `NvidiaTTSService`).

changelog/4208.removed.11.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.nim` package. Use `pipecat.services.nvidia.llm` instead (`NimLLMService` → `NvidiaLLMService`).

changelog/4208.removed.2.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.gemini_multimodal_live` package. Use `pipecat.services.google.gemini_live` instead. Note that class names no longer include "Multimodal" (e.g. `GeminiMultimodalLiveLLMService` → `GeminiLiveLLMService`).

changelog/4208.removed.3.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.aws_nova_sonic` package. Use `pipecat.services.aws.nova_sonic` instead.

changelog/4208.removed.4.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.openai_realtime` package. Use `pipecat.services.openai.realtime` instead.

changelog/4208.removed.5.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `OpenAIRealtimeBetaLLMService` and `AzureRealtimeBetaLLMService`. Use `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService` from `pipecat.services.openai.realtime` and `pipecat.services.azure.realtime` instead.

changelog/4208.removed.6.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.deepgram.stt_sagemaker` and `pipecat.services.deepgram.tts_sagemaker` modules. Use `pipecat.services.deepgram.sagemaker.stt` and `pipecat.services.deepgram.sagemaker.tts` instead.

changelog/4208.removed.7.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `GoogleLLMOpenAIBetaService` from `pipecat.services.google.openai`. Use `GoogleLLMService` from `pipecat.services.google.llm` instead.

changelog/4208.removed.8.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.google.llm_vertex` module. Use `pipecat.services.google.vertex.llm` instead.

changelog/4208.removed.9.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.google.gemini_live.llm_vertex` module. Use `pipecat.services.google.gemini_live.vertex.llm` instead.

changelog/4208.removed.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated `pipecat.services.ai_services` module. Import from `pipecat.services.ai_service`, `pipecat.services.llm_service`, `pipecat.services.stt_service`, `pipecat.services.tts_service`, etc. instead.

changelog/4209.changed.md

@@ -1 +0,0 @@
-- Changed `GrokLLMService` default model from `grok-3-beta` to `grok-3`, now that the model is generally available.

changelog/4213.changed.md

@@ -1 +0,0 @@
-- `GoogleImageGenService` now defaults to `imagen-4.0-generate-001` (previously `imagen-3.0-generate-002`).

changelog/4215.changed.md

@@ -1 +0,0 @@
-- ⚠️ `BaseOpenAILLMService.get_chat_completions()` now accepts an `LLMContext` instead of `OpenAILLMInvocationParams`. If you override this method, update your signature accordingly.

changelog/4215.removed.2.md

@@ -1,22 +0,0 @@
-- ⚠️ Removed deprecated service-specific context and aggregator machinery, which was superseded by the universal `LLMContext` system.
-
-  Service-specific classes removed: `AnthropicLLMContext`, `AnthropicContextAggregatorPair`, `AWSBedrockLLMContext`, `AWSBedrockContextAggregatorPair`, `OpenAIContextAggregatorPair`, and their user/assistant aggregators. Also removed `create_context_aggregator()` from `LLMService`, `OpenAILLMService`, `AnthropicLLMService`, and `AWSBedrockLLMService`.
-
-  Base aggregator classes removed (from `pipecat.processors.aggregators.llm_response`): `BaseLLMResponseAggregator`, `LLMContextResponseAggregator`, `LLMUserContextAggregator`, `LLMAssistantContextAggregator`, `LLMUserResponseAggregator`, `LLMAssistantResponseAggregator`.
-
-  From the developer's point of view, migrating will usually be a matter of going from this:
-
-  ```python
-  context = OpenAILLMContext(messages, tools)
-  context_aggregator = llm.create_context_aggregator(context)
-  ```
-
-  To this:
-
-  ```python
-  from pipecat.processors.aggregators.llm_context import LLMContext
-  from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-
-  context = LLMContext(messages, tools)
-  context_aggregator = LLMContextAggregatorPair(context)
-  ```

changelog/4215.removed.3.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated frame types `LLMMessagesFrame` and `OpenAILLMContextAssistantTimestampFrame` from `pipecat.frames.frames`. Instead of `LLMMessagesFrame`, use `LLMContextFrame` with the new messages, or `LLMMessagesUpdateFrame` with `run_llm=True`.

changelog/4215.removed.4.md

@@ -1 +0,0 @@
-- ⚠️ Removed `GatedOpenAILLMContextAggregator` (from `pipecat.processors.aggregators.gated_open_ai_llm_context`). Use `GatedLLMContextAggregator` (from `pipecat.processors.aggregators.gated_llm_context`) instead.

changelog/4215.removed.5.md

@@ -1 +0,0 @@
-- ⚠️ Removed `VisionImageFrameAggregator` (from `pipecat.processors.aggregators.vision_image_frame`). Vision/image handling is now built into `LLMContext` (from `pipecat.processors.aggregators.llm_context`). See the `12*` examples for the recommended replacement pattern.

changelog/4215.removed.6.md

@@ -1 +0,0 @@
-- ⚠️ Removed deprecated compatibility modules: `pipecat.services.openai_realtime_beta` (use `pipecat.services.openai.realtime`), `pipecat.services.openai_realtime.context`, `pipecat.services.openai_realtime.frames`, `pipecat.services.openai.realtime.context`, `pipecat.services.openai.realtime.frames`, `pipecat.services.gemini_multimodal_live` (use `pipecat.services.google.gemini_live`), `pipecat.services.aws_nova_sonic.context` (use `pipecat.services.aws.nova_sonic`), `pipecat.services.google.openai` and `pipecat.services.google.llm_openai` (use `pipecat.services.google.llm`).

changelog/4215.removed.md

@@ -1,18 +0,0 @@
-- ⚠️ Removed `OpenAILLMContext`, `OpenAILLMContextFrame`, and `OpenAILLMContext.from_messages()`. Use `LLMContext` (from `pipecat.processors.aggregators.llm_context`) and `LLMContextFrame` (from `pipecat.frames.frames`) instead. All services now exclusively use the universal `LLMContext`.
-
-  From the developer's point of view, migrating will usually be a matter of going from this:
-
-  ```python
-  context = OpenAILLMContext(messages, tools)
-  context_aggregator = llm.create_context_aggregator(context)
-  ```
-
-  To this:
-
-  ```python
-  from pipecat.processors.aggregators.llm_context import LLMContext
-  from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-
-  context = LLMContext(messages, tools)
-  context_aggregator = LLMContextAggregatorPair(context)
-  ```

changelog/4217.added.2.md

@@ -1 +0,0 @@
-- Added `group_parallel_tools` parameter to `LLMService` (default `True`). When `True`, all function calls from the same LLM response batch share a group ID and the LLM is triggered exactly once after the last call completes. Set to `False` to trigger inference independently for each function call result as it arrives.

changelog/4217.added.md

@@ -1 +0,0 @@
-- Added `is_async=True` support to `register_function()` and `register_direct_function()`. When enabled, the LLM continues the conversation immediately without waiting for the function result. The result is injected back into the context as a `developer` message once available, triggering a new LLM inference at that point.

changelog/4217.changed.md

@@ -1 +0,0 @@
-- When multiple function calls are returned in a single LLM response, the LLM is now triggered exactly once after the last call in the batch completes, rather than waiting for all function calls.

changelog/4217.fixed.2.md

@@ -1 +0,0 @@
-- Fixed `BaseOutputTransport` discarding pending `UninterruptibleFrame` items (e.g. function-call context updates) when an interruption arrived. The audio task is now kept alive and only interruptible frames are drained when uninterruptible frames are present in the queue.

changelog/4217.fixed.3.md

@@ -1 +0,0 @@
-- Fixed spurious LLM inference being triggered when a function call result arrived while the user was actively speaking. The context frame is now suppressed until the user stops speaking.

changelog/4217.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue where `UninterruptibleFrame` items queued in `FrameProcessor` could be incorrectly dropped on interruption. Previously only the frame currently being processed was checked; now the entire process queue is scanned so pending uninterruptible frames are always delivered.

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 gstreamer --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

docs/api/conf.py

@@ -48,6 +48,8 @@ autodoc_default_options = {
 # Mock imports for optional dependencies
 autodoc_mock_imports = [
     # Krisp - has build issues on some platforms
+    "pipecat_ai_krisp",
+    "krisp",
     "krisp_audio",
     # System-specific GUI libraries
     "_tkinter",
@@ -96,6 +98,7 @@ autodoc_mock_imports = [
     "cartesia",
     "camb",
     "sarvamai",
+    "openpipe",
     "openai.types.beta.realtime",
     "langchain_core",
     "langchain_core.messages",

env.example

@@ -80,6 +80,9 @@ GOOGLE_TEST_CREDENTIALS=...
 # Gradium
 GRAPDIUM_API_KEY=...
 
+# Grok
+GROK_API_KEY=...
+
 # Groq
 GROQ_API_KEY=...
 
@@ -121,21 +124,18 @@ MINIMAX_GROUP_ID=...
 # Mistral
 MISTRAL_API_KEY=...
 
-# Nebius
-NEBIUS_API_KEY=...
-
 # Neuphonic
 NEUPHONIC_API_KEY=...
 
-# Novita
-NOVITA_API_KEY=...
-
 # NVIDIA
 NVIDIA_API_KEY=...
 
 # OpenAI
 OPENAI_API_KEY=...
 
+# OpenPipe
+OPENPIPE_API_KEY=...
+
 # OpenRouter
 OPENROUTER_API_KEY=...
 
@@ -176,9 +176,6 @@ SENTRY_DSN=...
 SIMLI_API_KEY=...
 SIMLI_FACE_ID=...
 
-# Smallest
-SMALLEST_API_KEY=...
-
 # Smart turn
 LOCAL_SMART_TURN_MODEL_PATH=...
 FAL_SMART_TURN_API_KEY=...
@@ -212,6 +209,3 @@ WHATSAPP_TOKEN=...
 WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
 WHATSAPP_PHONE_NUMBER_ID=...
 WHATSAPP_APP_SECRET=...
-
-# xAI / Grok
-XAI_API_KEY=...

examples/README.md

@@ -1,150 +1,31 @@
 # Pipecat Examples
 
-This directory contains examples showing how to build voice and multimodal agents with Pipecat.
+This directory contains examples to help you learn how to build with Pipecat.
 
-## Setup
+## Getting Started
 
-1. Follow the [README](https://github.com/pipecat-ai/pipecat/blob/main/README.md#%EF%B8%8F-contributing-to-the-framework) steps to get your local environment configured.
+New to Pipecat? Start here:
 
-   > **Run from root directory**: Make sure you are running the steps from the root directory.
+- **[Quickstart](quickstart/)** - Get your first voice AI bot running in 5 minutes _(coming soon)_
+- **[Client/Server Web](client-server-web/)** - Learn to build web applications with Pipecat's client SDKs _(coming soon)_
+- **[Phone Bot with Twilio](phone-bot-twilio/)** - Connect your bot to a phone number _(coming soon)_
 
-   > **Using local audio?**: The `LocalAudioTransport` requires a system dependency for `portaudio`. Install the dependency to use the transport.
+## Foundational Examples
 
-2. Copy the [`env.example`](../env.example) file and add API keys for services you plan to use:
+Single-file examples that introduce core Pipecat concepts one at a time. These examples:
 
-   ```bash
-   cp env.example .env
-   # Edit .env with your API keys
-   ```
+- Build on each other progressively
+- Focus on specific features or integrations
+- Are used for testing with every Pipecat release
 
-3. Run any example:
+See the **[Foundational Examples README](foundational/)** for the complete list.
 
-   ```bash
-   uv run python getting-started/01-say-one-thing.py
-   ```
+## More Advanced Examples
 
-4. Open the web interface at http://localhost:7860/client/ and click "Connect"
+Ready to explore complex use cases? Visit **[pipecat-examples](https://github.com/pipecat-ai/pipecat-examples)** for:
 
-## Running examples with other transports
-
-Most examples support running with other transports, like Twilio or Daily.
-
-### Daily
-
-You need to create a Daily account at https://dashboard.daily.co/u/signup. Once signed up, you can create your own room from the dashboard and set the environment variables `DAILY_ROOM_URL` and `DAILY_API_KEY`. Alternatively, you can let the example create a room for you (still needs `DAILY_API_KEY` environment variable). Then, start any example with `-t daily`:
-
-```bash
-uv run getting-started/06-voice-agent.py -t daily
-```
-
-### Twilio
-
-It is also possible to run the example through a Twilio phone number. You will need to setup a few things:
-
-1. Install and run [ngrok](https://ngrok.com/download).
-
-```bash
-ngrok http 7860
-```
-
-2. Configure your Twilio phone number. One way is to setup a TwiML app and set the request URL to the ngrok URL from step (1). Then, set your phone number to use the new TwiML app.
-
-Then, run the example with:
-
-```bash
-uv run getting-started/06-voice-agent.py -t twilio -x NGROK_HOST_NAME
-```
-
-## Directory Structure
-
-### [`getting-started/`](./getting-started/)
-
-Progressive introduction to Pipecat, from minimal TTS to a full voice agent with function calling.
-
-### [`voice/`](./voice/)
-
-Full STT + LLM + TTS voice agent pipelines showcasing different speech service providers (Deepgram, ElevenLabs, Cartesia, etc.)
-
-### [`function-calling/`](./function-calling/)
-
-Function calling with different LLM providers (OpenAI, Anthropic, Google, etc.)
-
-### [`transcription/`](./transcription/)
-
-Speech-to-text examples with various STT providers.
-
-### [`vision/`](./vision/)
-
-Image description and vision capabilities with different multimodal LLMs.
-
-### [`realtime/`](./realtime/)
-
-Realtime and multimodal live APIs (OpenAI Realtime, Gemini Live, AWS Nova Sonic, Ultravox, Grok).
-
-### [`persistent-context/`](./persistent-context/)
-
-Maintaining conversation context across sessions with different providers.
-
-### [`context-summarization/`](./context-summarization/)
-
-Summarizing conversation context to manage token limits.
-
-### [`update-settings/`](./update-settings/)
-
-Changing service settings at runtime, organized by service type:
-
-- **[`stt/`](./update-settings/stt/)** — Speech-to-text settings
-- **[`tts/`](./update-settings/tts/)** — Text-to-speech settings
-- **[`llm/`](./update-settings/llm/)** — LLM settings
-
-### [`turn-management/`](./turn-management/)
-
-Turn detection, interruption handling, and user input management.
-
-### [`thinking-and-mcp/`](./thinking-and-mcp/)
-
-LLM thinking/reasoning modes and MCP (Model Context Protocol) tool server integration.
-
-### [`transports/`](./transports/)
-
-Transport layer examples (WebRTC, Daily, LiveKit).
-
-### [`video-avatar/`](./video-avatar/)
-
-Video avatar integrations (Tavus, HeyGen, Simli, LemonSlice).
-
-### [`video-processing/`](./video-processing/)
-
-Video processing, mirroring, GStreamer, and custom video tracks.
-
-### [`audio/`](./audio/)
-
-Audio recording, background sounds, and sound effects.
-
-### [`observability/`](./observability/)
-
-Pipeline monitoring: observers, heartbeats, and Sentry metrics.
-
-### [`rag/`](./rag/)
-
-Retrieval-augmented generation, grounding, and long-term memory (Mem0, Gemini).
-
-### [`features/`](./features/)
-
-Miscellaneous features: wake phrases, live translation, service switching, voice switching, and more.
-
-## Advanced Usage
-
-### Customizing Network Settings
-
-```bash
-uv run python <example-name> --host 0.0.0.0 --port 8080
-```
-
-### Troubleshooting
-
-- **No audio/video**: Check browser permissions for microphone and camera
-- **Connection errors**: Verify API keys in `.env` file
-- **Port conflicts**: Use `--port` to change the port
-
-For more examples, visit the [pipecat-examples repository](https://github.com/pipecat-ai/pipecat-examples).
+- Production-ready applications
+- Multi-platform client implementations
+- Telephony integrations
+- Multimodal and creative applications
+- Deployment and monitoring examples

examples/foundational/01-say-one-thing-piper.py

@@ -0,0 +1,71 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+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.piper.tts import PiperHttpTTSService
+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 use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(audio_out_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
+    "webrtc": lambda: TransportParams(audio_out_enabled=True),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        tts = PiperHttpTTSService(
+            base_url=os.getenv("PIPER_BASE_URL"),
+            aiohttp_session=session,
+            sample_rate=24000,
+        )
+
+        task = PipelineTask(
+            Pipeline([tts, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
+
+        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/01-say-one-thing-rime.py

@@ -0,0 +1,72 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+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.rime.tts import RimeHttpTTSService
+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 use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(audio_out_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
+    "webrtc": lambda: TransportParams(audio_out_enabled=True),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        tts = RimeHttpTTSService(
+            api_key=os.getenv("RIME_API_KEY", ""),
+            aiohttp_session=session,
+            settings=RimeHttpTTSService.Settings(
+                voice="rex",
+            ),
+        )
+
+        task = PipelineTask(
+            Pipeline([tts, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
+
+        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/01b-livekit-audio.py

@@ -0,0 +1,64 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.runner.livekit import configure
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    (url, token, room_name) = await configure()
+
+    transport = LiveKitTransport(
+        url=url,
+        token=token,
+        room_name=room_name,
+        params=LiveKitParams(audio_out_enabled=True),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
+
+    runner = PipelineRunner()
+
+    task = PipelineTask(Pipeline([tts, transport.output()]))
+
+    # Register an event handler so we can play the audio when the
+    # participant joins.
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant_id):
+        await asyncio.sleep(1)
+        await task.queue_frame(
+            TTSSpeakFrame(
+                "Hello there! How are you doing today? Would you like to talk about the weather?"
+            )
+        )
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,64 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+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.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
+
+load_dotenv(override=True)
+
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(audio_out_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
+    "webrtc": lambda: TransportParams(audio_out_enabled=True),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+    task = PipelineTask(
+        Pipeline([tts, transport.output()]),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    # Register an event handler so we can play the audio when the client joins
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
+
+    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/02-llm-say-one-thing.py

@@ -60,7 +60,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         context = LLMContext()
-        context.add_message({"role": "developer", "content": "Say hello to the world."})
+        context.add_message({"role": "user", "content": "Say hello to the world."})
         await task.queue_frames([LLMContextFrame(context), EndFrame()])
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

examples/foundational/03-still-frame.py

@@ -0,0 +1,84 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+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.fal.image import FalImageGenService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+    ),
+    "webrtc": lambda: TransportParams(
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        imagegen = FalImageGenService(
+            settings=FalImageGenService.Settings(
+                image_size="square_hd",
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        task = PipelineTask(
+            Pipeline([imagegen, transport.output()]),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            await task.queue_frame(TextFrame("a cat in the style of picasso"))
+
+        @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/04-transports-small-webrtc.py

@@ -109,9 +109,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        context.add_message(
-            {"role": "developer", "content": "Please introduce yourself to the user."}
-        )
+        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")