Add changelog for PR #3851

Remove processing metrics (ProcessingMetricsData)
Processing metrics were an early addition that predated a clear understanding of what timing measurements matter in real-time pipelines. They were inconsistently implemented across services, often broken, and overlapped with the better-defined TTFB metric. - Remove ProcessingMetricsData class and all start/stop_processing_metrics methods from FrameProcessorMetrics, FrameProcessor, and SentryMetrics - Remove all processing metrics calls from 31 service files (LLM, TTS, STT, image, vision, realtime) - Clean up empty _start_metrics() stubs left in STT services - Remove processing metrics handling from RTVI, metrics log observer, pipeline task initial metrics, and strands agents framework - Update tests and examples Remaining metrics (TTFB, LLM token usage, TTS character usage, text aggregation time) are well-defined and consistently implemented.
2026-02-26 18:27:50 -05:00 · 2026-02-26 18:20:49 -05:00
658 changed files with 17539 additions and 40367 deletions
--- a/.claude/skills/changelog/SKILL.md
+++ b/.claude/skills/changelog/SKILL.md
@@ -32,20 +32,6 @@ Create changelog files for the important commits in this PR. The PR number is pr

 6. Use ⚠️ emoji prefix for breaking changes.

-7. **Write changes in user-facing terms first.** Lead with what users of the framework will notice: new APIs, changed behavior, new parameters, fixed bugs they might have hit, etc. Implementation details (internal refactoring, how something is wired up under the hood) can be included as secondary context after the user-facing description, but should never be the *only* content of a changelog entry when there is a user-visible effect.
-
-   **Good** (user-facing first, implementation detail as context):
-   ```
-   - Turn completion instructions now persist correctly across full context updates when using `system_instruction`. Previously they were injected as a context system message, which caused warning spam and didn't survive context updates.
-   ```
-
-   **Bad** (implementation detail only, no user-facing framing):
-   ```
-   - Fixed turn completion instructions being injected as a context system message instead of using `system_instruction`.
-   ```
-
-   Ask yourself: "If I'm a developer building on Pipecat, what would I notice changed?" Start there.
-
 ## Example

 For PR #3519 with a new feature and a bug fix:
@@ -57,5 +43,5 @@ For PR #3519 with a new feature and a bug fix:

 `changelog/3519.fixed.md`:
 ```
- Fixed an issue where something was not working correctly in some user-visible scenario. The root cause was an internal implementation detail.
+- Fixed an issue where something was not working correctly.
 ```
--- a/.claude/skills/update-docs/SKILL.md
+++ b/.claude/skills/update-docs/SKILL.md
@@ -157,11 +157,7 @@ After processing all mapped pairs, check for two kinds of gaps:

 **Missing sections**: Mapped doc pages that are missing standard sections compared to the source. For example, a transport page with no Configuration section, or a service page with no InputParams table when the source defines `InputParams(BaseModel)`. Flag these and offer to add the missing sections.

-If the user wants a new page, do all three of the following:
-
-#### 8a: Create the doc page
-
-Create the new `.mdx` file using this template structure:
+If the user wants a new page, create it using this template structure:
 ```
 ---
 title: "Service Name"
@@ -211,53 +207,6 @@ pip install "pipecat-ai[package-name]"
 [Event table and example code]
 ```

-#### 8b: Add to docs.json
-
-Add the new page path to `DOCS_PATH/docs.json` in the correct navigation group. The path format is `server/services/{category}/{provider}` (without the `.mdx` extension).
-
-Find the matching group in the navigation structure:
- **STT** → `"group": "Speech-to-Text"` under Services
- **TTS** → `"group": "Text-to-Speech"` under Services
- **LLM** → `"group": "LLM"` under Services
- **S2S** → `"group": "Speech-to-Speech"` under Services
- **Transport** → `"group": "Transport"` under Services
- **Serializer** → `"group": "Serializers"` under Services
- **Image generation** → `"group": "Image Generation"` under Services
- **Video** → `"group": "Video"` under Services
- **Memory** → `"group": "Memory"` under Services
- **Vision** → `"group": "Vision"` under Services
- **Analytics** → `"group": "Analytics & Monitoring"` under Services
-
-Insert the new entry **alphabetically** within the group's `pages` array. For example, adding a new STT service "foo":
-```json
-{
-  "group": "Speech-to-Text",
-  "pages": [
-    "server/services/stt/assemblyai",
-    "server/services/stt/aws",
-    ...
-    "server/services/stt/foo",
-    ...
-  ]
-}
-```
-
-#### 8c: Add to supported-services.mdx
-
-Add a new row to the correct category table in `DOCS_PATH/server/services/supported-services.mdx`.
-
-Use this format:
-```
-| [DisplayName](/server/services/{category}/{provider}) | `pip install "pipecat-ai[package]"` |
-```
-
-To determine the correct values:
- **DisplayName**: Use the service's human-readable name (e.g., "ElevenLabs", "AWS Polly", "Google Gemini")
- **package**: Look at the service's `pyproject.toml` extras or the import pattern in the source code. For example, if the service is in `src/pipecat/services/foo/`, the package is typically `foo`.
- If no pip dependencies are required, use `No dependencies required` instead.
-
-Insert the new row **alphabetically** within the table. Match the column alignment of the existing rows.
-
 ### Step 9: Output summary

 After all edits are complete, print a summary:
@@ -272,9 +221,6 @@ After all edits are complete, print a summary:
 ### Updated guides
 - `guides/learn/speech-to-text.mdx` — Updated code example (renamed `old_param` → `new_param`)

-### New service pages
- `server/services/tts/newprovider.mdx` — Created page, added to docs.json (Text-to-Speech), added to supported-services.mdx
-
 ### Unmapped source files
 - `src/pipecat/services/newprovider/tts.py` — NewProviderTTSService (no doc page exists)

@@ -301,6 +247,4 @@ Before finishing, verify:
 - [ ] New parameters have accurate types and defaults from source
 - [ ] Formatting matches the existing page style
 - [ ] Guides referencing changed APIs were checked and updated
- [ ] New service pages were added to `docs.json` in the correct group, alphabetically
- [ ] New service pages were added to `supported-services.mdx` in the correct table, alphabetically
 - [ ] Unmapped files were reported to the user
--- a/.github/workflows/update-docs.yml
+++ b/.github/workflows/update-docs.yml
@@ -1,147 +0,0 @@
-name: Update Documentation on PR Merge
-
-on:
-  pull_request_target:
-    types: [closed]
-    branches: [main]
-    paths:
-      - "src/pipecat/services/**"
-      - "src/pipecat/transports/**"
-      - "src/pipecat/serializers/**"
-      - "src/pipecat/processors/**"
-      - "src/pipecat/audio/**"
-      - "src/pipecat/turns/**"
-      - "src/pipecat/observers/**"
-      - "src/pipecat/pipeline/**"
-  workflow_dispatch:
-    inputs:
-      pr_number:
-        description: "PR number to generate docs for"
-        required: true
-        type: string
-
-jobs:
-  update-docs:
-    if: >-
-      github.event_name == 'workflow_dispatch' ||
-      github.event.pull_request.merged == true
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    permissions:
-      contents: read
-      pull-requests: read
-      id-token: write
-    steps:
-      - name: Checkout pipecat
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Checkout docs
-        uses: actions/checkout@v4
-        with:
-          repository: pipecat-ai/docs
-          token: ${{ secrets.DOCS_SYNC_TOKEN }}
-          path: _docs
-
-      - name: Resolve PR number
-        id: pr
-        run: |
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            echo "number=${{ inputs.pr_number }}" >> "$GITHUB_OUTPUT"
-          else
-            echo "number=${{ github.event.pull_request.number }}" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Update documentation
-        uses: anthropics/claude-code-action@v1
-        env:
-          DOCS_SYNC_TOKEN: ${{ secrets.DOCS_SYNC_TOKEN }}
-        with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          prompt: |
-            You are updating documentation for the pipecat-ai/docs repository based on
-            changes merged in PR #${{ steps.pr.outputs.number }} of pipecat-ai/pipecat.
-
-            ## Setup
-
-            1. Read the skill instructions at `.claude/skills/update-docs/SKILL.md`
-            2. Read the source-to-doc mapping at `.claude/skills/update-docs/SOURCE_DOC_MAPPING.md`
-            3. The docs repository is checked out at `./_docs/`
-
-            ## Get the diff
-
-            Run `gh pr diff ${{ steps.pr.outputs.number }}` to see what changed in the PR.
-            Also run `gh pr diff ${{ steps.pr.outputs.number }} --name-only` to get the list of changed files.
-            Filter to source files matching the directories listed in SKILL.md Step 3.
-
-            If no relevant source files were changed, exit with "No documentation changes needed."
-
-            ## Follow the skill instructions
-
-            Apply the SKILL.md workflow (Steps 3-9) with these adaptations for automation:
-
-            ### Docs path
-            Use `./_docs/` — it's already checked out. Do not ask for a path.
-
-            ### Branch management
-            - Branch name: `docs/pr-${{ steps.pr.outputs.number }}`
-            - Work inside `./_docs/` for all doc edits and git operations
-            - Check if the branch already exists on the remote:
-              ```bash
-              cd _docs && git fetch origin docs/pr-${{ steps.pr.outputs.number }} 2>/dev/null
-              ```
-              - If it exists: check it out (supports workflow re-runs)
-              - If not: create it from main
-
-            ### Git config
-            Before committing in `_docs`, set:
-            ```bash
-            git config user.name "github-actions[bot]"
-            git config user.email "github-actions[bot]@users.noreply.github.com"
-            ```
-
-            ### No interactive questions
-            Do not ask questions. If you encounter gaps (unmapped files, missing sections,
-            ambiguous changes), note them in the PR body under "## Gaps identified".
-
-            ### Creating the docs PR
-            After committing all changes in `_docs`, push and create a PR:
-            ```bash
-            cd _docs
-            git push -u origin docs/pr-${{ steps.pr.outputs.number }}
-            GH_TOKEN=$DOCS_SYNC_TOKEN gh pr create \
-              --repo pipecat-ai/docs \
-              --label auto-docs \
-              --title "docs: update for pipecat PR #${{ steps.pr.outputs.number }}" \
-              --body "$(cat <<'BODY'
-            Automated documentation update for [pipecat PR #${{ steps.pr.outputs.number }}](https://github.com/pipecat-ai/pipecat/pull/${{ steps.pr.outputs.number }}).
-
-            ## Changes
-            <summarize each doc page updated and what changed>
-
-            ## Gaps identified
-            <any unmapped files, missing doc pages, or missing sections — or "None">
-            BODY
-            )"
-            ```
-
-            ### Re-run handling
-            If `gh pr create` fails because a PR from that branch already exists,
-            push the updated commits and use `gh pr edit` to update the body instead.
-
-            ### No-op
-            If after analyzing the diff you determine no documentation changes are needed
-            (e.g., only skip-listed files changed, or changes don't affect public API docs),
-            exit cleanly without creating a branch or PR. Output "No documentation changes needed."
-
-            ## Important rules
-            - Only modify files inside `./_docs/` — never modify pipecat source code
-            - Follow the conservative editing rules from SKILL.md Step 6
-            - Read each doc page fully before editing (SKILL.md Guidelines)
-            - Use `GH_TOKEN=$DOCS_SYNC_TOKEN` for all `gh` commands targeting pipecat-ai/docs
-          claude_args: |
-            --model claude-sonnet-4-5-20250929
-            --max-turns 30
-            --allowedTools "Read,Write,Edit,Glob,Grep,Bash"
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,964 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 <!-- towncrier release notes start -->

-## [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
-
- Added concurrent audio context support: `CartesiaTTSService` can now
-  synthesize the next sentence while the previous one is still playing, by
-  setting `pause_frame_processing=False` and routing each sentence through its
-  own audio context queue.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
- Added custom video track support to Daily transport. Use
-  `video_out_destinations` in `DailyParams` to publish multiple video tracks
-  simultaneously, mirroring the existing `audio_out_destinations` feature.
-  (PR [#3831](https://github.com/pipecat-ai/pipecat/pull/3831))
-
- Added `ServiceSwitcherStrategyFailover` that automatically switches to the
-  next service when the active service reports a non-fatal error. Recovery
-  policies can be implemented via the `on_service_switched` event handler.
-  (PR [#3861](https://github.com/pipecat-ai/pipecat/pull/3861))
-
- Added optional `timeout_secs` parameter to `register_function()` and
-  `register_direct_function()` for per-tool function call timeout control,
-  overriding the global `function_call_timeout_secs` default.
-  (PR [#3915](https://github.com/pipecat-ai/pipecat/pull/3915))
-
- Added `cloud-audio-only` recording option to Daily transport's
-  `enable_recording` property.
-  (PR [#3916](https://github.com/pipecat-ai/pipecat/pull/3916))
-
- Wired up `system_instruction` in `BaseOpenAILLMService`,
-  `AnthropicLLMService`, and `AWSBedrockLLMService` so it works as a default
-  system prompt, matching the behavior of the Google services. This enables
-  sharing a single `LLMContext` across multiple LLM services, where each
-  service provides its own system instruction independently.
-
-    ```python
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful assistant.",
-    )
-
-    context = LLMContext()
-
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        context.add_message({"role": "user", "content": "Please introduce yourself."})
-        await task.queue_frames([LLMRunFrame()])
-    ```
-  (PR [#3918](https://github.com/pipecat-ai/pipecat/pull/3918))
-
- Added `vad_threshold` parameter to `AssemblyAIConnectionParams` for
-  configuring voice activity detection sensitivity in U3 Pro. Aligning this
-  with external VAD thresholds (e.g., Silero VAD) prevents the "dead zone"
-  where AssemblyAI transcribes speech that VAD hasn't detected yet.
-  (PR [#3927](https://github.com/pipecat-ai/pipecat/pull/3927))
-
- Added `push_empty_transcripts` parameter to `BaseWhisperSTTService` and
-  `OpenAISTTService` to allow empty transcripts to be pushed downstream as
-  `TranscriptionFrame` instead of discarding them (the default behavior). This
-  is intended for situations where VAD fires even though the user did not
-  speak. In these cases, it is useful to know that nothing was transcribed so
-  that the agent can resume speaking, instead of waiting longer for a
-  transcription.
-  (PR [#3930](https://github.com/pipecat-ai/pipecat/pull/3930))
-
- LLM services (`BaseOpenAILLMService`, `AnthropicLLMService`,
-  `AWSBedrockLLMService`) now log a warning when both `system_instruction` and
-  a system message in the context are set. The constructor's
-  `system_instruction` takes precedence.
-  (PR [#3932](https://github.com/pipecat-ai/pipecat/pull/3932))
-
- Runtime settings updates (via `STTUpdateSettingsFrame`) now work for AWS
-  Transcribe, Azure, Cartesia, Deepgram, ElevenLabs Realtime, Gradium, and
-  Soniox STT services. Previously, changing settings at runtime only stored the
-  new values without reconnecting.
-  (PR [#3946](https://github.com/pipecat-ai/pipecat/pull/3946))
-
- Exposed `on_summary_applied` event on `LLMAssistantAggregator`, allowing
-  users to listen for context summarization events without accessing private
-  members.
-  (PR [#3947](https://github.com/pipecat-ai/pipecat/pull/3947))
-
- Deepgram Flux STT settings (`keyterm`, `eot_threshold`,
-  `eager_eot_threshold`, `eot_timeout_ms`) can now be updated mid-stream via
-  `STTUpdateSettingsFrame` without triggering a reconnect. The new values are
-  sent to Deepgram as a Configure WebSocket message on the existing connection.
-  (PR [#3953](https://github.com/pipecat-ai/pipecat/pull/3953))
-
- Added `system_instruction` parameter to `run_inference` across all LLM
-  services, allowing callers to override the system prompt for one-shot
-  inference calls. Used by `_generate_summary` to pass the summarization prompt
-  cleanly.
-  (PR [#3968](https://github.com/pipecat-ai/pipecat/pull/3968))
-
-### Changed
-
- Audio context management (previously in `AudioContextTTSService`) is now
-  built into `TTSService`. All WebSocket providers (`cartesia`, `elevenlabs`,
-  `asyncai`, `inworld`, `rime`, `gradium`, `resembleai`) now inherit from
-  `WebsocketTTSService` directly. Word-timestamp baseline is set automatically
-  on the first audio chunk of each context instead of requiring each provider
-  to call `start_word_timestamps()` in their receive loop.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
- Daily transport now uses `CustomVideoSource`/`CustomVideoTrack` instead of
-  `VirtualCameraDevice` for the default camera output, mirroring how audio
-  already works with `CustomAudioSource`/`CustomAudioTrack`.
-  (PR [#3831](https://github.com/pipecat-ai/pipecat/pull/3831))
-
- ⚠️ Updated `DeepgramSTTService` to use `deepgram-sdk` v6. The `LiveOptions`
-  class was removed from the SDK and is now provided by pipecat directly;
-  import it from `pipecat.services.deepgram.stt` instead of `deepgram`.
-  (PR [#3848](https://github.com/pipecat-ai/pipecat/pull/3848))
-
- `ServiceSwitcherStrategy` base class now provides a `handle_error()` hook for
-  subclasses to implement error-based switching. `ServiceSwitcher` defaults to
-  `ServiceSwitcherStrategyManual` and `strategy_type` is now optional.
-  (PR [#3861](https://github.com/pipecat-ai/pipecat/pull/3861))
-
- Support for Voice Focus 2.0 models.
-    - Updated `aic-sdk` to `~=2.1.0` to support Voice Focus 2.0 models.
-    - Cleaned unused `ParameterFixedError` exception handling in `AICFilter`
-      parameter setup.
-  (PR [#3889](https://github.com/pipecat-ai/pipecat/pull/3889))
-
- `max_context_tokens` and `max_unsummarized_messages` in
-  `LLMAutoContextSummarizationConfig` (and deprecated
-  `LLMContextSummarizationConfig`) can now be set to `None` independently to
-  disable that summarization threshold. At least one must remain set.
-  (PR [#3914](https://github.com/pipecat-ai/pipecat/pull/3914))
-
- ⚠️ Removed `formatted_finals` and `word_finalization_max_wait_time` from
-  `AssemblyAIConnectionParams` as these were v2 API parameters not supported in
-  v3. Clarified that `format_turns` only applies to Universal-Streaming models;
-  U3 Pro has automatic formatting built-in.
-  (PR [#3927](https://github.com/pipecat-ai/pipecat/pull/3927))
-
- Changed `DeepgramTTSService` to send a Clear message on interruption instead
-  of disconnecting and reconnecting the WebSocket, allowing the connection to
-  persist throughout the session.
-  (PR [#3958](https://github.com/pipecat-ai/pipecat/pull/3958))
-
- Re-added `enhancement_level` support to `AICFilter` with runtime
-  `FilterEnableFrame` control, applying `ProcessorParameter.Bypass` and
-  `ProcessorParameter.EnhancementLevel` together.
-  (PR [#3961](https://github.com/pipecat-ai/pipecat/pull/3961))
-
- Updated `daily-python` dependency from `~=0.23.0` to `~=0.24.0`.
-  (PR [#3970](https://github.com/pipecat-ai/pipecat/pull/3970))
-
- Updated `FishAudioTTSService` default model from `s1` to `s2-pro`, matching
-  Fish Audio's latest recommended model for improved quality and speed.
-  (PR [#3973](https://github.com/pipecat-ai/pipecat/pull/3973))
-
- `AzureSTTService` `region` parameter is now optional when `private_endpoint`
-  is provided. A `ValueError` is raised if neither is given, and a warning is
-  logged if both are provided (`private_endpoint` takes priority).
-  (PR [#3974](https://github.com/pipecat-ai/pipecat/pull/3974))
-
-### Deprecated
-
- Deprecated `AudioContextTTSService` and `AudioContextWordTTSService`.
-  Subclass `WebsocketTTSService` directly instead; audio context management is
-  now part of the base `TTSService`.
-  - Deprecated `WordTTSService`, `WebsocketWordTTSService`, and
-    `InterruptibleWordTTSService`. Word timestamp logic is now always active in
-    `TTSService` and no longer needs to be opted into via a subclass.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
- Deprecated `pipecat.services.google.llm_vertex`,
-  `pipecat.services.google.llm_openai`, and
-  `pipecat.services.google.gemini_live.llm_vertex` modules. Use
-  `pipecat.services.google.vertex.llm`, `pipecat.services.google.openai.llm`,
-  and `pipecat.services.google.gemini_live.vertex.llm` instead. The old import
-  paths still work but will emit a `DeprecationWarning`.
-  (PR [#3980](https://github.com/pipecat-ai/pipecat/pull/3980))
-
-### Removed
-
- ⚠️ Removed `supports_word_timestamps` parameter from `TTSService.__init__()`.
-  Word timestamp logic is now always active. Remove this argument from any
-  custom subclass `super().__init__()` calls.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
-### Fixed
-
- Fixed `DeepgramSTTService` keepalive ping timeout disconnections. The
-  deepgram-sdk v6 removed automatic keepalive; pipecat now sends explicit
-  `KeepAlive` messages every 5 seconds, within the recommended 3–5 second
-  interval before Deepgram's 10-second inactivity timeout.
-  (PR [#3848](https://github.com/pipecat-ai/pipecat/pull/3848))
-
- Fixed `BufferError: Existing exports of data: object cannot be re-sized` in
-  `AICFilter` caused by holding a `memoryview` on the mutable audio buffer
-  across async yield points.
-  (PR [#3889](https://github.com/pipecat-ai/pipecat/pull/3889))
-
- Fixed TTS context not being appended to the assistant message history when
-  using `TTSSpeakFrame` with `append_to_context=True` with some TTS providers.
-  (PR [#3936](https://github.com/pipecat-ai/pipecat/pull/3936))
-
- Fixed context summarization leaving orphaned tool responses in the kept
-  context when tool calls were moved to the summarized portion.
-  (PR [#3937](https://github.com/pipecat-ai/pipecat/pull/3937))
-
- Fixed turn completion state not resetting at end of LLM responses.
-  `LLMFullResponseEndFrame` is pushed (not received) by the LLM service, so the
-  mixin now handles it in `push_frame` instead of `process_frame`.
-  (PR [#3956](https://github.com/pipecat-ai/pipecat/pull/3956))
-
- Fixed turn completion instructions being injected as a context system message
-  instead of using `system_instruction`. This caused warning spam when
-  `system_instruction` was also set and didn't persist across full context
-  updates.
-  (PR [#3957](https://github.com/pipecat-ai/pipecat/pull/3957))
-
- Fixed `TTSService` audio context queue getting blocked when
-  `append_to_audio_context()` was called with a `None` context ID, which
-  prevented subsequent audio from being delivered.
-  (PR [#3958](https://github.com/pipecat-ai/pipecat/pull/3958))
-
- Fixed `on_call_state_updated` event handler in LiveKit transport receiving
-  incorrect number of arguments due to redundant `self` passed to
-  `_call_event_handler`.
-  (PR [#3959](https://github.com/pipecat-ai/pipecat/pull/3959))
-
- Fixed OpenAI Realtime, OpenAI Realtime Beta, and Grok realtime services
-  treating `conversation_already_has_active_response` as a fatal error. These
-  services now log it as a non-fatal debug event when a response is already in
-  progress.
-  (PR [#3960](https://github.com/pipecat-ai/pipecat/pull/3960))
-
- Fixed `SmallWebRTCConnection` silently discarding messages sent before the
-  data channel is open by queuing them and flushing once the channel is ready.
-  A bounded queue (`MAX_MESSAGE_QUEUE_SIZE = 50`) prevents unbounded memory
-  growth, and a 10-second timeout after connection clears the queue and falls
-  back to discard mode if the data channel never opens.
-  (PR [#3962](https://github.com/pipecat-ai/pipecat/pull/3962))
-
- Fixed `AzureSTTService` failing to initialize when `private_endpoint` is
-  provided. The Azure Speech SDK's `SpeechConfig` does not accept both `region`
-  and `endpoint` simultaneously, so they are now passed conditionally.
-  (PR [#3967](https://github.com/pipecat-ai/pipecat/pull/3967))
-
- Fixed `GoogleLLMService` ignoring the `system_instruction` set via
-  constructor or `GoogleLLMSettings` when a system message was also present in
-  the context. The settings value now correctly takes priority, and a warning
-  is logged when both are set.
-  (PR [#3976](https://github.com/pipecat-ai/pipecat/pull/3976))
-
-### Other
-
- Updated foundational examples to use `system_instruction` on LLM services
-  instead of adding system messages to `LLMContext`.
-  (PR [#3918](https://github.com/pipecat-ai/pipecat/pull/3918))
-
- Updated AssemblyAI turn detection example to use `keyterms_prompt` list
-  format instead of `prompt` string for improved clarity.
-  (PR [#3929](https://github.com/pipecat-ai/pipecat/pull/3929))
-
- Updated foundational examples and eval scripts to use `"user"` role instead
-  of `"system"` when adding messages to `LLMContext`, since system prompts
-  should be set via `system_instruction` on the LLM service.
-  (PR [#3931](https://github.com/pipecat-ai/pipecat/pull/3931))
-
-## [0.0.104] - 2026-03-02
-
-### Added
-
- Added `TextAggregationMetricsData` metric measuring the time from the first
-  LLM token to the first complete sentence, representing the latency cost of
-  sentence aggregation in the TTS pipeline.
-  (PR [#3696](https://github.com/pipecat-ai/pipecat/pull/3696))
-
- Added support for using strongly-typed objects instead of dicts for updating
-  service settings at runtime.
-
-    Instead of, say:
-
-    ```python
-    await task.queue_frame(
-        STTUpdateSettingsFrame(settings={"language": Language.ES})
-    )
-    ```
-
-    you'd do:
-
-    ```python
-    await task.queue_frame(
-        STTUpdateSettingsFrame(delta=DeepgramSTTSettings(language=Language.ES))
-    )
-    ```
-
-  Each service now vends strongly-typed classes like `DeepgramSTTSettings`
-  representing the service's runtime-updatable settings.
-  (PR [#3714](https://github.com/pipecat-ai/pipecat/pull/3714))
-
- Added support for specifying private endpoints for Azure Speech-to-Text,
-  enabling use in private networks behind firewalls.
-  (PR [#3764](https://github.com/pipecat-ai/pipecat/pull/3764))
-
- Added `LemonSliceTransport` and `LemonSliceApi` to support adding real-time
-  LemonSlice Avatars to any Daily room.
-  (PR [#3791](https://github.com/pipecat-ai/pipecat/pull/3791))
-
- Added `output_medium` parameter to `AgentInputParams` and
-  `OneShotInputParams` in Ultravox service to control initial output medium
-  (text or voice) at call creation time.
-  (PR [#3806](https://github.com/pipecat-ai/pipecat/pull/3806))
-
- Added `TurnMetricsData` as a generic metrics class for turn detection, with
-  e2e processing time measurement. `KrispVivaTurn` now emits `TurnMetricsData`
-  with `e2e_processing_time_ms` tracking the interval from VAD
-  speech-to-silence transition to turn completion.
-  (PR [#3809](https://github.com/pipecat-ai/pipecat/pull/3809))
-
- Added `on_audio_context_interrupted()` and `on_audio_context_completed()`
-  callbacks to `AudioContextTTSService`. Subclasses can override these to
-  perform provider-specific cleanup instead of overriding
-  `_handle_interruption()`.
-  (PR [#3814](https://github.com/pipecat-ai/pipecat/pull/3814))
-
- Added `on_summary_applied` event to `LLMContextSummarizer` for observability,
-  providing message counts before and after context summarization.
-  (PR [#3855](https://github.com/pipecat-ai/pipecat/pull/3855))
-
- Added `summary_message_template` to `LLMContextSummarizationConfig` for
-  customizing how summaries are formatted when injected into context (e.g.,
-  wrapping in XML tags).
-  (PR [#3855](https://github.com/pipecat-ai/pipecat/pull/3855))
-
- Added `summarization_timeout` to `LLMContextSummarizationConfig` (default
-  120s) to prevent hung LLM calls from permanently blocking future
-  summarizations.
-  (PR [#3855](https://github.com/pipecat-ai/pipecat/pull/3855))
-
- Added optional `llm` field to `LLMContextSummarizationConfig` for routing
-  summarization to a dedicated LLM service (e.g., a cheaper/faster model)
-  instead of the pipeline's primary model.
-  (PR [#3855](https://github.com/pipecat-ai/pipecat/pull/3855))
-
- Add AssemblyAI u3-rt-pro model support with built-in turn detection mode
-  (PR [#3856](https://github.com/pipecat-ai/pipecat/pull/3856))
-
- Added `LLMSummarizeContextFrame` to trigger on-demand context summarization
-  from anywhere in the pipeline (e.g. a function call tool). Accepts an
-  optional `config: LLMContextSummaryConfig` to override summary generation
-  settings per request.
-  (PR [#3863](https://github.com/pipecat-ai/pipecat/pull/3863))
-
- Added `LLMContextSummaryConfig` (summary generation params:
-  `target_context_tokens`, `min_messages_after_summary`,
-  `summarization_prompt`) and `LLMAutoContextSummarizationConfig` (auto-trigger
-  thresholds: `max_context_tokens`, `max_unsummarized_messages`, plus a nested
-  `summary_config`). These replace the monolithic
-  `LLMContextSummarizationConfig`.
-  (PR [#3863](https://github.com/pipecat-ai/pipecat/pull/3863))
-
- Added support for the `speed_alpha` parameter to the `arcana` model in
-  `RimeTTSService`.
-  (PR [#3873](https://github.com/pipecat-ai/pipecat/pull/3873))
-
- Added `ClientConnectedFrame`, a new `SystemFrame` pushed by all transports
-  (Daily, LiveKit, FastAPI WebSocket, WebSocket Server, SmallWebRTC, HeyGen,
-  Tavus) when a client connects. Enables observers to track transport readiness
-  timing.
-  (PR [#3881](https://github.com/pipecat-ai/pipecat/pull/3881))
-
- Added `StartupTimingObserver` for measuring how long each processor's
-  `start()` method takes during pipeline startup. Also measures transport
-  readiness — the time from `StartFrame` to first client connection — via the
-  `on_transport_timing_report` event.
-  (PR [#3881](https://github.com/pipecat-ai/pipecat/pull/3881))
-
- Added `BotConnectedFrame` for SFU transports and `on_transport_timing_report`
-  event to `StartupTimingObserver` with bot and client connection timing.
-  (PR [#3881](https://github.com/pipecat-ai/pipecat/pull/3881))
-
- Added optional `direction` parameter to `PipelineTask.queue_frame()` and
-  `PipelineTask.queue_frames()`, allowing frames to be pushed upstream from the
-  end of the pipeline.
-  (PR [#3883](https://github.com/pipecat-ai/pipecat/pull/3883))
-
- Added `on_latency_breakdown` event to `UserBotLatencyObserver` providing
-  per-service TTFB, text aggregation, user turn duration, and function call
-  latency metrics for each user-to-bot response cycle.
-  (PR [#3885](https://github.com/pipecat-ai/pipecat/pull/3885))
-
- Added `on_first_bot_speech_latency` event to `UserBotLatencyObserver`
-  measuring the time from client connection to first bot speech. An
-  `on_latency_breakdown` is also emitted for this first speech event.
-  (PR [#3885](https://github.com/pipecat-ai/pipecat/pull/3885))
-
- Added `broadcast_interruption()` to `FrameProcessor`. This method pushes an
-  `InterruptionFrame` both upstream and downstream directly from the calling
-  processor, avoiding the round-trip through the pipeline task that
-  `push_interruption_task_frame_and_wait()` required.
-  (PR [#3896](https://github.com/pipecat-ai/pipecat/pull/3896))
-
-### Changed
-
- Added `text_aggregation_mode` parameter to `TTSService` and all TTS
-  subclasses with a new `TextAggregationMode` enum (`SENTENCE`, `TOKEN`). All
-  text now flows through text aggregators regardless of mode, enabling pattern
-  detection and tag handling in TOKEN mode.
-  (PR [#3696](https://github.com/pipecat-ai/pipecat/pull/3696))
-
- ⚠️ Refactored runtime-updatable service settings to use strongly-typed
-  classes (`TTSSettings`, `STTSettings`, `LLMSettings`, and service-specific
-  subclasses) instead of plain dicts. Each service's `_settings` now holds
-  these strongly-typed objects. For service maintainers, see changes in
-  COMMUNITY_INTEGRATIONS.md.
-  (PR [#3714](https://github.com/pipecat-ai/pipecat/pull/3714))
-
- Word timestamp support has been moved from `WordTTSService` into `TTSService`
-  via a new `supports_word_timestamps` parameter. Services that previously
-  extended `WordTTSService`, `AudioContextWordTTSService`, or
-  `WebsocketWordTTSService` now pass `supports_word_timestamps=True` to their
-  parent `__init__` instead.
-  (PR [#3786](https://github.com/pipecat-ai/pipecat/pull/3786))
-
- Improved Ultravox TTFB measurement accuracy by using VAD speech end time
-  instead of `UserStoppedSpeakingFrame` timing.
-  (PR [#3806](https://github.com/pipecat-ai/pipecat/pull/3806))
-
- Aligned `UltravoxRealtimeLLMService` frame handling with OpenAI/Gemini
-  realtime services: added `InterruptionFrame` handling with metrics cleanup,
-  processing metrics at response boundaries, and improved agent transcript
-  handling for both voice and text output modalities.
-  (PR [#3806](https://github.com/pipecat-ai/pipecat/pull/3806))
-
- Updated `OpenAIRealtimeLLMService` default model to `gpt-realtime-1.5`.
-  (PR [#3807](https://github.com/pipecat-ai/pipecat/pull/3807))
-
- Added `api_key` parameter to `KrispVivaSDKManager`, `KrispVivaTurn`, and
-  `KrispVivaFilter` for Krisp SDK v1.6.1+ licensing. Falls back to
-  `KRISP_VIVA_API_KEY` environment variable.
-  (PR [#3809](https://github.com/pipecat-ai/pipecat/pull/3809))
-
- Bumped `nltk` minimum version from 3.9.1 to 3.9.3 to resolve a security
-  vulnerability.
-  (PR [#3811](https://github.com/pipecat-ai/pipecat/pull/3811))
-
- `ServiceSettingsUpdateFrame`s are now `UninterruptibleFrame`s. Generally
-  speaking, you don't want a user interruption to prevent a service setting
-  change from going into effect. Note that you usually don't use
-  `ServiceSettingsUpdateFrame` directly, you use one of its subclasses:
-    - `LLMUpdateSettingsFrame`
-    - `TTSUpdateSettingsFrame`
-    - `STTUpdateSettingsFrame`
-  (PR [#3819](https://github.com/pipecat-ai/pipecat/pull/3819))
-
- Updated context summarization to use `user` role instead of `assistant` for
-  summary messages.
-  (PR [#3855](https://github.com/pipecat-ai/pipecat/pull/3855))
-
- Rename `AssemblyAISTTService` parameter
-  `min_end_of_turn_silence_when_confident` parameter to `min_turn_silence` (old
-  name still supported with deprecation warning)
-  (PR [#3856](https://github.com/pipecat-ai/pipecat/pull/3856))
-
- ⚠️ Renamed `LLMAssistantAggregatorParams` fields:
-  `enable_context_summarization` → `enable_auto_context_summarization` and
-  `context_summarization_config` → `auto_context_summarization_config` (now
-  accepts `LLMAutoContextSummarizationConfig`). The old names still work with a
-  `DeprecationWarning` for one release cycle.
-  (PR [#3863](https://github.com/pipecat-ai/pipecat/pull/3863))
-
- `ElevenLabsRealtimeSTTService` now sets `TranscriptionFrame.finalized` to
-  `True` when using `CommitStrategy.MANUAL`.
-  (PR [#3865](https://github.com/pipecat-ai/pipecat/pull/3865))
-
- Updated numba version pin from == to >=0.61.2
-  (PR [#3868](https://github.com/pipecat-ai/pipecat/pull/3868))
-
- Updated tracing code to use `ServiceSettings` dataclass API
-  (`given_fields()`, attribute access) instead of dict-style access
-  (`.items()`, `in`, subscript).
-  (PR [#3879](https://github.com/pipecat-ai/pipecat/pull/3879))
-
- ⚠️ Removed `event` field and `complete()` method from `InterruptionFrame`.
-  Removed `event` field from `InterruptionTaskFrame`. These are no longer
-  needed since `broadcast_interruption()` does not require a round-trip
-  completion signal.
-  (PR [#3896](https://github.com/pipecat-ai/pipecat/pull/3896))
-
- Moved `pipecat.services.deepgram.stt_sagemaker` and
-  `pipecat.services.deepgram.tts_sagemaker` to
-  `pipecat.services.deepgram.sagemaker.stt` and
-  `pipecat.services.deepgram.sagemaker.tts`. The old import paths still work
-  but emit a `DeprecationWarning`.
-  (PR [#3902](https://github.com/pipecat-ai/pipecat/pull/3902))
-
-### Deprecated
-
- ⚠️ Deprecated `aggregate_sentences` parameter on `TTSService` and all TTS
-  subclasses. Use `text_aggregation_mode=TextAggregationMode.SENTENCE` or
-  `text_aggregation_mode=TextAggregationMode.TOKEN` instead.
-  (PR [#3696](https://github.com/pipecat-ai/pipecat/pull/3696))
-
- Deprecated `set_model()`, `set_voice()`, and `set_language()` on AI services
-  in favor of runtime updates via `TTSUpdateSettingsFrame`,
-  `STTUpdateSettingsFrame`, and `LLMUpdateSettingsFrame`.
-
-  ⚠️ Note, too, a subtle behavior change in these deprecated methods. Whereas
-  previously only `set_language()` caused the service to actually react to the
-  update (e.g. by reconnecting to a remote service so it an pick up the
-  change), now all these methods do. This change was made as part of a refactor
-  making them all work the same way under the hood.
-  (PR [#3714](https://github.com/pipecat-ai/pipecat/pull/3714))
-
- Dict-based `*UpdateSettingsFrame(settings={...})` is deprecated in favor of
-  passing typed settings delta objects with
-  `*UpdateSettingsFrame(delta={...})`.
-  (PR [#3714](https://github.com/pipecat-ai/pipecat/pull/3714))
-
- Deprecated `WordTTSService`, `WebsocketWordTTSService`,
-  `AudioContextWordTTSService`, and `InterruptibleWordTTSService`. Use their
-  non-word counterparts with `supports_word_timestamps=True` instead:
-    - `WordTTSService` → `TTSService(supports_word_timestamps=True)`
-    - `WebsocketWordTTSService` →
-  `WebsocketTTSService(supports_word_timestamps=True)`
-    - `AudioContextWordTTSService` →
-  `AudioContextTTSService(supports_word_timestamps=True)`
-    - `InterruptibleWordTTSService` →
-  `InterruptibleTTSService(supports_word_timestamps=True)`
-  (PR [#3786](https://github.com/pipecat-ai/pipecat/pull/3786))
-
- Deprecated `SmartTurnMetricsData` in favor of `TurnMetricsData`.
-  `BaseSmartTurn` now emits `TurnMetricsData` directly.
-  (PR [#3809](https://github.com/pipecat-ai/pipecat/pull/3809))
-
- Deprecated `LLMContextSummarizationConfig`. Use
-  `LLMAutoContextSummarizationConfig` with a nested `LLMContextSummaryConfig`
-  instead. The old class emits a `DeprecationWarning`.
-  (PR [#3863](https://github.com/pipecat-ai/pipecat/pull/3863))
-
- Deprecated `push_interruption_task_frame_and_wait()` in `FrameProcessor`. Use
-  `broadcast_interruption()` instead. The old method now delegates to
-  `broadcast_interruption()` and logs a deprecation warning.
-  (PR [#3896](https://github.com/pipecat-ai/pipecat/pull/3896))
-
-### Removed
-
- Removed `local-smart-turn-v3` optional extra from `pyproject.toml`. The
-  `transformers` and `onnxruntime` packages are now always installed as core
-  dependencies since they are required by the default turn stop strategy,
-  `TurnAnalyzerUserTurnStopStrategy` which uses `LocalSmartTurnAnalyzerV3`.
-  (PR [#3803](https://github.com/pipecat-ai/pipecat/pull/3803))
-
- ⚠️ Removed `PlayHTTTSService` and `PlayHTHttpTTSService`. PlayHT has been
-  shut down and is no longer available.
-  (PR [#3838](https://github.com/pipecat-ai/pipecat/pull/3838))
-
-### Fixed
-
- Added `LLMSpecificMessage` handling in `LLMContextSummarizationUtil` to skip
-  provider-specific messages during context summarization.
-  (PR [#3794](https://github.com/pipecat-ai/pipecat/pull/3794))
-
- Treated `response_cancel_not_active` as a non-fatal error in realtime
-  services (`OpenAIRealtimeLLMService`, `GrokRealtimeLLMService`,
-  `OpenAIRealtimeBetaLLMService`) to prevent WebSocket disconnection when
-  cancelling an inactive response.
-  (PR [#3795](https://github.com/pipecat-ai/pipecat/pull/3795))
-
- Fixed Poetry compatibility by inlining `local-smart-turn-v3` dependencies
-  (`transformers`, `onnxruntime`) into core dependencies instead of using a
-  self-referential extra.
-  (PR [#3803](https://github.com/pipecat-ai/pipecat/pull/3803))
-
- Fixed `SentryMetrics` method signatures to match updated
-  `FrameProcessorMetrics` base class, resolving `TypeError` when using
-  `start_time`/`end_time` keyword arguments.
-  (PR [#3808](https://github.com/pipecat-ai/pipecat/pull/3808))
-
- Fixed STT TTFB metrics not being reported for `SonioxSTTService` and
-  `AWSTranscribeSTTService` due to missing `can_generate_metrics()` override.
-  (PR [#3813](https://github.com/pipecat-ai/pipecat/pull/3813))
-
- Fixed an issue where `AudioContextTTSService`-based providers (AsyncAI,
-  ElevenLabs, Inworld, Rime) did not close or clean up their server-side audio
-  contexts after normal speech completion, only on interruption.
-  (PR [#3814](https://github.com/pipecat-ai/pipecat/pull/3814))
-
- Fixed STT TTFB metrics measuring timeout expiry time instead of actual
-  transcript arrival time.
-  (PR [#3822](https://github.com/pipecat-ai/pipecat/pull/3822))
-
- Fixed `InterimTranscriptionFrame` and `TranslationFrame` being
-  unintentionally pushed downstream in `LLMUserAggregator`. They are now
-  consumed like `TranscriptionFrame`.
-  (PR [#3825](https://github.com/pipecat-ai/pipecat/pull/3825))
-
- Fixed misleading "Empty audio frame received for STT service" warnings when
-  using audio filters (e.g. `RNNoiseFilter`, `KrispVivaFilter`, `AICFilter`)
-  that buffer audio internally.
-  (PR [#3828](https://github.com/pipecat-ai/pipecat/pull/3828))
-
- Fixed issues with `RimeNonJsonTTSService` where trailing punctuation is
-  sometimes vocalized
-  (PR [#3837](https://github.com/pipecat-ai/pipecat/pull/3837))
-
- Fixed `TTSSpeakFrame` not committing spoken text to the conversation context
-  when used outside of an LLM response (e.g., bot greetings or injected
-  speech).
-  (PR [#3845](https://github.com/pipecat-ai/pipecat/pull/3845))
-
- Removed verbose per-chunk audio logging from `GenesysAudioHookSerializer`
-  that flooded production logs.
-  (PR [#3850](https://github.com/pipecat-ai/pipecat/pull/3850))
-
- Add beta feature warning when using custom prompts with AssemblyAI
-  (PR [#3856](https://github.com/pipecat-ai/pipecat/pull/3856))
-
- Fixed `LocalSmartTurnAnalyzerV3` producing incorrect end-of-turn predictions
-  at non-16kHz sample rates (e.g. 8kHz Twilio telephony) by adding automatic
-  resampling to 16kHz before Whisper feature extraction.
-  (PR [#3857](https://github.com/pipecat-ai/pipecat/pull/3857))
-
- Fixed `PipelineTask` double-inserting `RTVIProcessor` into the frame chain
-  when the user provides both an `RTVIProcessor` in the pipeline and a custom
-  `RTVIObserver` subclass in observers.
-  (PR [#3867](https://github.com/pipecat-ai/pipecat/pull/3867))
-
- Fixed turn completion instructions being lost when `LLMMessagesUpdateFrame`
-  replaces the LLM context. When `filter_incomplete_user_turns` is enabled, the
-  turn completion system message is now re-injected after context replacement.
-  (PR [#3888](https://github.com/pipecat-ai/pipecat/pull/3888))
-
- Fixed Azure TTS and STT services silently swallowing cancellation errors
-  (invalid API key, network failures, rate limiting) instead of propagating
-  them as `ErrorFrame`s to the pipeline.
-  (PR [#3893](https://github.com/pipecat-ai/pipecat/pull/3893))
-
-### Performance
-
- Switched `GradiumTTSService` from `InterruptibleWordTTSService` to
-  `AudioContextWordTTSService`, eliminating websocket disconnect/reconnect on
-  every interruption by using `client_req_id`-based multiplexing.
-  (PR [#3759](https://github.com/pipecat-ai/pipecat/pull/3759))
-
-### Other
-
- Standardized Sarvam STT/TTS User-Agent header handling to consistently send
-  Pipecat SDK identity in websocket requests.
-  (PR [#3886](https://github.com/pipecat-ai/pipecat/pull/3886))
-
 ## [0.0.103] - 2026-02-20

 ### Added
--- a/COMMUNITY_INTEGRATIONS.md
+++ b/COMMUNITY_INTEGRATIONS.md
@@ -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

@@ -217,9 +200,9 @@ 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

@@ -248,105 +231,49 @@ def can_generate_metrics(self) -> bool:
    return True
 ```

-### Service Settings
+### Dynamic Settings Updates

-Every AI service (STT, LLM, TTS, image generation, etc.) exposes a **Settings dataclass** that serves two roles:
+STT, LLM, and TTS services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).

-1. **Store mode** — the service's `self._settings` holds the current value of every runtime-updatable field.
-2. **Delta mode** — an update frame (e.g. `TTSUpdateSettingsFrame`) specifies only the fields that should change; unspecified fields remain `NOT_GIVEN`.
-
-#### Defining your Settings class
-
-Extend `STTSettings`, `TTSSettings`, `LLMSettings`, or `ImageGenSettings` (or, if your service directly subclasses `AIService`, `ServiceSettings`). The base classes already provide common fields (e.g. `model`, `voice`, `language`). You only need to add **service-specific knobs that should be runtime-updatable**:
+Each service declares a settings dataclass that extends the appropriate base (`STTSettings`, `TTSSettings`, `LLMSettings`). Fields default to `NOT_GIVEN` so that update objects can represent sparse deltas:

 ```python
 from dataclasses import dataclass, field

-from pipecat.services.settings import TTSSettings, NOT_GIVEN
+from pipecat.services.settings import STTSettings, NOT_GIVEN

@dataclass
-class MyTTSSettings(TTSSettings):
-    """Settings for MyTTS service.
+class MySTTSettings(STTSettings):
+    """Settings for my STT service.

    Parameters:
-        speaking_rate: Speed multiplier (0.5–2.0).
+        region: Cloud region for the service.
    """

-    speaking_rate: float | None = field(default_factory=lambda: NOT_GIVEN)
+    region: str = field(default_factory=lambda: NOT_GIVEN)
 ```

-**What goes in Settings vs. `__init__` params:**
-
-| Belongs in Settings                                      | Stays as `__init__` params                |
-| -------------------------------------------------------- | ----------------------------------------- |
-| Model name, voice, language                              | API keys, auth tokens                     |
-| Service-specific tuning knobs (rate, pitch, temperature) | Base URLs, endpoint overrides             |
-| Anything users may want to change mid-session            | Audio encoding, sample format             |
-|                                                          | Connection parameters (timeouts, retries) |
-
-The rule of thumb: if a caller might send an update frame to change it at runtime, it belongs in Settings. Everything else is init-only config stored as `self._xxx`.
-
-#### Wiring settings into `__init__`
-
-Accept an **optional** `settings` parameter. Build a `default_settings` object with all fields set to real values, then merge any caller overrides with `apply_update`.
-
-Add a `Settings` **class attribute** that points to your settings dataclass. This lets callers access the settings class through the service itself (e.g. `MyTTSService.Settings(...)`) without a separate import:
+The service stores its current settings in `self._settings` and declares the type with a class-level annotation for editor support:

 ```python
-from typing import Optional
+class MySTTService(STTService):
+    _settings: MySTTSettings

-class MyTTSService(TTSService):
-    Settings = MyTTSSettings
-    _settings: Settings
-
-    def __init__(
-        self,
-        *,
-        api_key: str,
-        settings: Optional[Settings] = None,
-        **kwargs,
-    ):
-        # 1. Defaults — every field has a real value (store mode).
-        default_settings = self.Settings(
-            model="my-model-v1",
-            voice="default-voice",
-            language="en",
-            speaking_rate=1.0,
+    def __init__(self, *, model: str, language: str, region: str, **kwargs):
+        # An initial value should be provided for every settings field.
+        # This will be validated at service start.
+        # (If you track sample_rate, it can be a placeholder value like 0; see
+        # "Sample Rate Handling").
+        super().__init__(
+            settings=MySTTSettings(model=model, language=language, region=region), **kwargs
        )
-
-        # 2. Merge caller overrides (only given fields win).
-        if settings is not None:
-            default_settings.apply_update(settings)
-
-        # 3. Pass the fully-populated settings to the base class.
-        super().__init__(settings=default_settings, **kwargs)
-
-        # 4. Init-only config stored separately.
-        self._api_key = api_key
 ```

-This pattern lets callers override only what they care about:
-
-```python
-# Uses all defaults
-svc = MyTTSService(api_key="sk-xxx")
-
-# Overrides just the voice — access Settings through the service class
-svc = MyTTSService(
-    api_key="sk-xxx",
-    settings=MyTTSService.Settings(voice="custom-voice"),
-)
-```
-
-#### Reacting to runtime changes
-
-AI services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
-
 To react to runtime setting changes, override `_update_settings`. The base implementation applies the delta to `self._settings` and returns a `dict` mapping each changed field name to its **pre-update** value. Your override should call `super()` first, then act on the changed fields. A common implementation might look like:

 ```python
-async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
-    """Apply a settings update, reconfiguring the connection if needed."""
+async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
+    """Apply a settings update, reconfiguring the recognizer if needed."""
    changed = await super()._update_settings(update)

    if not changed:
@@ -365,7 +292,7 @@ Note that, in this example, the service requires a reconnect to apply the new la
 If your service can't yet apply certain settings at runtime, call `self._warn_unhandled_updated_settings(changed)` with any unhandled field names so users get a clear log message:

 ```python
-async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
+async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
    changed = await super()._update_settings(update)

    if not changed:
@@ -398,7 +325,7 @@ 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

@@ -420,15 +347,17 @@ 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
 ```
--- a/README.md
+++ b/README.md
@@ -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.
@@ -85,20 +81,19 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout

 ## 🧩 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), [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), [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), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-| 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), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [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), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [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), [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)

--- a/changelog/3696.added.md
+++ b/changelog/3696.added.md
@@ -0,0 +1 @@
+- Added `TextAggregationMetricsData` metric measuring the time from the first LLM token to the first complete sentence, representing the latency cost of sentence aggregation in the TTS pipeline.
--- a/changelog/3696.changed.md
+++ b/changelog/3696.changed.md
@@ -0,0 +1 @@
+- Added `text_aggregation_mode` parameter to `TTSService` and all TTS subclasses with a new `TextAggregationMode` enum (`SENTENCE`, `TOKEN`). All text now flows through text aggregators regardless of mode, enabling pattern detection and tag handling in TOKEN mode.
--- a/changelog/3696.deprecated.md
+++ b/changelog/3696.deprecated.md
@@ -0,0 +1 @@
+- ⚠️ Deprecated `aggregate_sentences` parameter on `TTSService` and all TTS subclasses. Use `text_aggregation_mode=TextAggregationMode.SENTENCE` or `text_aggregation_mode=TextAggregationMode.TOKEN` instead.
--- a/changelog/3714.added.md
+++ b/changelog/3714.added.md
@@ -0,0 +1,19 @@
+- Added support for using strongly-typed objects instead of dicts for updating service settings at runtime.
+
+  Instead of, say:
+
+  ```python
+  await task.queue_frame(
+      STTUpdateSettingsFrame(settings={"language": Language.ES})
+  )
+  ```
+
+  you'd do:
+
+  ```python
+  await task.queue_frame(
+      STTUpdateSettingsFrame(delta=DeepgramSTTSettings(language=Language.ES))
+  )
+  ```
+
+  Each service now vends strongly-typed classes like `DeepgramSTTSettings` representing the service's runtime-updatable settings.
--- a/changelog/3714.changed.md
+++ b/changelog/3714.changed.md
@@ -0,0 +1 @@
+- ⚠️ Refactored runtime-updatable service settings to use strongly-typed classes (`TTSSettings`, `STTSettings`, `LLMSettings`, and service-specific subclasses) instead of plain dicts. Each service's `_settings` now holds these strongly-typed objects. For service maintainers, see changes in COMMUNITY_INTEGRATIONS.md.
--- a/changelog/3714.deprecated.2.md
+++ b/changelog/3714.deprecated.2.md
@@ -0,0 +1 @@
+- Dict-based `*UpdateSettingsFrame(settings={...})` is deprecated in favor of passing typed settings delta objects with `*UpdateSettingsFrame(delta={...})`.
--- a/changelog/3714.deprecated.md
+++ b/changelog/3714.deprecated.md
@@ -0,0 +1,3 @@
+- Deprecated `set_model()`, `set_voice()`, and `set_language()` on AI services in favor of runtime updates via `TTSUpdateSettingsFrame`, `STTUpdateSettingsFrame`, and `LLMUpdateSettingsFrame`.
+
+  ⚠️ Note, too, a subtle behavior change in these deprecated methods. Whereas previously only `set_language()` caused the service to actually react to the update (e.g. by reconnecting to a remote service so it an pick up the change), now all these methods do. This change was made as part of a refactor making them all work the same way under the hood.
--- a/changelog/3759.performance.md
+++ b/changelog/3759.performance.md
@@ -0,0 +1 @@
+- Switched `GradiumTTSService` from `InterruptibleWordTTSService` to `AudioContextWordTTSService`, eliminating websocket disconnect/reconnect on every interruption by using `client_req_id`-based multiplexing.
--- a/changelog/3786.changed.md
+++ b/changelog/3786.changed.md
@@ -0,0 +1 @@
+- Word timestamp support has been moved from `WordTTSService` into `TTSService` via a new `supports_word_timestamps` parameter. Services that previously extended `WordTTSService`, `AudioContextWordTTSService`, or `WebsocketWordTTSService` now pass `supports_word_timestamps=True` to their parent `__init__` instead.
--- a/changelog/3786.deprecated.md
+++ b/changelog/3786.deprecated.md
@@ -0,0 +1,5 @@
+- Deprecated `WordTTSService`, `WebsocketWordTTSService`, `AudioContextWordTTSService`, and `InterruptibleWordTTSService`. Use their non-word counterparts with `supports_word_timestamps=True` instead:
+  - `WordTTSService` → `TTSService(supports_word_timestamps=True)`
+  - `WebsocketWordTTSService` → `WebsocketTTSService(supports_word_timestamps=True)`
+  - `AudioContextWordTTSService` → `AudioContextTTSService(supports_word_timestamps=True)`
+  - `InterruptibleWordTTSService` → `InterruptibleTTSService(supports_word_timestamps=True)`
--- a/changelog/3803.fixed.md
+++ b/changelog/3803.fixed.md
@@ -0,0 +1 @@
+- Fixed Poetry compatibility by inlining `local-smart-turn-v3` dependencies (`transformers`, `onnxruntime`) into core dependencies instead of using a self-referential extra.
--- a/changelog/3803.removed.md
+++ b/changelog/3803.removed.md
@@ -0,0 +1 @@
+- Removed `local-smart-turn-v3` optional extra from `pyproject.toml`. The `transformers` and `onnxruntime` packages are now always installed as core dependencies since they are required by the default turn stop strategy, `TurnAnalyzerUserTurnStopStrategy` which uses `LocalSmartTurnAnalyzerV3`.
--- a/changelog/3806.added.md
+++ b/changelog/3806.added.md
@@ -0,0 +1 @@
+- Added `output_medium` parameter to `AgentInputParams` and `OneShotInputParams` in Ultravox service to control initial output medium (text or voice) at call creation time.
--- a/changelog/3806.changed.2.md
+++ b/changelog/3806.changed.2.md
@@ -0,0 +1 @@
+- Improved Ultravox TTFB measurement accuracy by using VAD speech end time instead of `UserStoppedSpeakingFrame` timing.
--- a/changelog/3806.changed.md
+++ b/changelog/3806.changed.md
@@ -0,0 +1 @@
+- Aligned `UltravoxRealtimeLLMService` frame handling with OpenAI/Gemini realtime services: added `InterruptionFrame` handling with metrics cleanup, processing metrics at response boundaries, and improved agent transcript handling for both voice and text output modalities.
--- a/changelog/3807.changed.md
+++ b/changelog/3807.changed.md
@@ -0,0 +1 @@
+- Updated `OpenAIRealtimeLLMService` default model to `gpt-realtime-1.5`.
--- a/changelog/3808.fixed.md
+++ b/changelog/3808.fixed.md
@@ -0,0 +1 @@
+- Fixed `SentryMetrics` method signatures to match updated `FrameProcessorMetrics` base class, resolving `TypeError` when using `start_time`/`end_time` keyword arguments.
--- a/changelog/3809.added.md
+++ b/changelog/3809.added.md
@@ -0,0 +1 @@
+- Added `TurnMetricsData` as a generic metrics class for turn detection, with e2e processing time measurement. `KrispVivaTurn` now emits `TurnMetricsData` with `e2e_processing_time_ms` tracking the interval from VAD speech-to-silence transition to turn completion.
--- a/changelog/3809.changed.md
+++ b/changelog/3809.changed.md
@@ -0,0 +1 @@
+- Added `api_key` parameter to `KrispVivaSDKManager`, `KrispVivaTurn`, and `KrispVivaFilter` for Krisp SDK v1.6.1+ licensing. Falls back to `KRISP_VIVA_API_KEY` environment variable.
--- a/changelog/3809.deprecated.md
+++ b/changelog/3809.deprecated.md
@@ -0,0 +1 @@
+- Deprecated `SmartTurnMetricsData` in favor of `TurnMetricsData`. `BaseSmartTurn` now emits `TurnMetricsData` directly.
--- a/changelog/3811.changed.md
+++ b/changelog/3811.changed.md
@@ -0,0 +1 @@
+- Bumped `nltk` minimum version from 3.9.1 to 3.9.3 to resolve a security vulnerability.
--- a/changelog/3813.fixed.md
+++ b/changelog/3813.fixed.md
@@ -0,0 +1 @@
+- Fixed STT TTFB metrics not being reported for `SonioxSTTService` and `AWSTranscribeSTTService` due to missing `can_generate_metrics()` override.
--- a/changelog/3814.added.md
+++ b/changelog/3814.added.md
@@ -0,0 +1 @@
+- Added `on_audio_context_interrupted()` and `on_audio_context_completed()` callbacks to `AudioContextTTSService`. Subclasses can override these to perform provider-specific cleanup instead of overriding `_handle_interruption()`.
--- a/changelog/3814.fixed.md
+++ b/changelog/3814.fixed.md
@@ -0,0 +1 @@
+- Fixed an issue where `AudioContextTTSService`-based providers (AsyncAI, ElevenLabs, Inworld, Rime) did not close or clean up their server-side audio contexts after normal speech completion, only on interruption.
--- a/changelog/3819.changed.md
+++ b/changelog/3819.changed.md
@@ -0,0 +1,4 @@
+- `ServiceSettingsUpdateFrame`s are now `UninterruptibleFrame`s. Generally speaking, you don't want a user interruption to prevent a service setting change from going into effect. Note that you usually don't use `ServiceSettingsUpdateFrame` directly, you use one of its subclasses:
+  - `LLMUpdateSettingsFrame`
+  - `TTSUpdateSettingsFrame`
+  - `STTUpdateSettingsFrame`
--- a/changelog/3822.fixed.md
+++ b/changelog/3822.fixed.md
@@ -0,0 +1 @@
+- Fixed STT TTFB metrics measuring timeout expiry time instead of actual transcript arrival time.
--- a/changelog/3825.fixed.md
+++ b/changelog/3825.fixed.md
@@ -0,0 +1 @@
+- Fixed `InterimTranscriptionFrame` and `TranslationFrame` being unintentionally pushed downstream in `LLMUserAggregator`. They are now consumed like `TranscriptionFrame`.
--- a/changelog/3828.fixed.md
+++ b/changelog/3828.fixed.md
@@ -0,0 +1 @@
+- Fixed misleading "Empty audio frame received for STT service" warnings when using audio filters (e.g. `RNNoiseFilter`, `KrispVivaFilter`, `AICFilter`) that buffer audio internally.
--- a/changelog/3837.fixed.md
+++ b/changelog/3837.fixed.md
@@ -0,0 +1 @@
+- Fixed issues with `RimeNonJsonTTSService` where trailing punctuation is sometimes vocalized
--- a/changelog/3838.removed.md
+++ b/changelog/3838.removed.md
@@ -0,0 +1 @@
+- ⚠️ Removed `PlayHTTTSService` and `PlayHTHttpTTSService`. PlayHT has been shut down and is no longer available.
--- a/changelog/3851.removed.md
+++ b/changelog/3851.removed.md
@@ -0,0 +1 @@
+- ⚠️ Removed `ProcessingMetricsData` and all `start_processing_metrics()`/`stop_processing_metrics()` methods from `FrameProcessor` and `FrameProcessorMetrics`. These metrics were inconsistently implemented across services and overlapped with the better-defined TTFB metric. TTFB, LLM token usage, TTS character usage, and text aggregation metrics are unaffected.
--- a/changelog/3978.added.md
+++ b/changelog/3978.added.md
@@ -1 +0,0 @@
- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`, `sarvam-105b` and `sarvam-105b-32k`
--- a/changelog/4013.added.md
+++ b/changelog/4013.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4013.changed.md
+++ b/changelog/4013.changed.md
@@ -1 +0,0 @@
- Added context prewarming path for `InworldTTSService` to improve first audio latency
--- a/changelog/4022.changed.md
+++ b/changelog/4022.changed.md
@@ -1 +0,0 @@
- Added `KrispVivaVadAnalyzer` for Voice Activity Detection using the Krisp VIVA SDK (requires `krisp_audio`).
--- a/changelog/4028.changed.md
+++ b/changelog/4028.changed.md
@@ -1 +0,0 @@
- Modeified `InworldTTSService` to close context at end of turn instead of relying on idle timeout
--- a/changelog/4031.added.md
+++ b/changelog/4031.added.md
@@ -1 +0,0 @@
- Added `XAIHttpTTSService` for text-to-speech using xAI's HTTP TTS API.
--- a/changelog/4078.changed.md
+++ b/changelog/4078.changed.md
@@ -1 +0,0 @@
- Added Gemini 3 support to the Gemini Live service.
--- a/changelog/4084.changed.md
+++ b/changelog/4084.changed.md
@@ -1 +0,0 @@
- `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.
--- a/changelog/4089.added.md
+++ b/changelog/4089.added.md
@@ -1 +0,0 @@
- 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).
--- a/changelog/4089.changed.md
+++ b/changelog/4089.changed.md
@@ -1 +0,0 @@
- ⚠️ `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.
--- a/changelog/4089.fixed.2.md
+++ b/changelog/4089.fixed.2.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4089.fixed.md
+++ b/changelog/4089.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4092.added.md
+++ b/changelog/4092.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4113.changed.md
+++ b/changelog/4113.changed.md
@@ -1 +0,0 @@
- Fixed `InworldTtsService` to fallback to full text when TTS timestamps are not received
--- a/changelog/4115.added.md
+++ b/changelog/4115.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4117.added.md
+++ b/changelog/4117.added.md
@@ -1 +0,0 @@
- Added `domain` parameter to `AssemblyAISTTSettings` for specialized recognition modes such as Medical Mode (`domain="medical-v1"`).
--- a/changelog/4119.added.md
+++ b/changelog/4119.added.md
@@ -1 +0,0 @@
- Added `NovitaLLMService` for using Novita AI's LLM models via their OpenAI-compatible API.
--- a/changelog/4120.added.md
+++ b/changelog/4120.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4125.fixed.md
+++ b/changelog/4125.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4126.fixed.md
+++ b/changelog/4126.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4127.fixed.md
+++ b/changelog/4127.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4128.added.md
+++ b/changelog/4128.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4130.changed.md
+++ b/changelog/4130.changed.md
@@ -1 +0,0 @@
- ⚠️ 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.
--- a/changelog/4135.fixed.md
+++ b/changelog/4135.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4136.changed.2.md
+++ b/changelog/4136.changed.2.md
@@ -1 +0,0 @@
- Bumped `nvidia-riva-client` minimum version to `>=2.25.1`.
--- a/changelog/4136.changed.md
+++ b/changelog/4136.changed.md
@@ -1 +0,0 @@
- Upgraded `protobuf` from 5.x to 6.x (`>=6.31.1,<7`).
--- a/changelog/4137.changed.md
+++ b/changelog/4137.changed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4142.changed.md
+++ b/changelog/4142.changed.md
@@ -1 +0,0 @@
- `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`).
--- a/changelog/4142.deprecated.md
+++ b/changelog/4142.deprecated.md
@@ -1 +0,0 @@
- `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.
--- a/changelog/4143.added.md
+++ b/changelog/4143.added.md
@@ -1 +0,0 @@
- Added `DeepgramFluxSageMakerSTTService` for running Deepgram Flux speech-to-text on AWS SageMaker endpoints.  Use with `ExternalUserTurnStrategies` to take advantage of Flux's turn detection.
--- a/changelog/4145.fixed.2.md
+++ b/changelog/4145.fixed.2.md
@@ -1 +0,0 @@
- Fixed websocket TTS word timestamps so interrupted contexts cannot leak stale words or backward PTS values into later turns.
--- a/changelog/4145.fixed.md
+++ b/changelog/4145.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4145.removed.md
+++ b/changelog/4145.removed.md
@@ -1 +0,0 @@
- ⚠️ `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.
--- a/changelog/4146.fixed.md
+++ b/changelog/4146.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4147.fixed.md
+++ b/changelog/4147.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4149.fixed.md
+++ b/changelog/4149.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4151.fixed.md
+++ b/changelog/4151.fixed.md
@@ -1 +0,0 @@
- Fixed `LiveKitOutputTransport` not clearing the `rtc.AudioSource` internal buffer on interruption, causing the bot to continue speaking for several seconds after being interrupted.
--- a/changelog/4152.fixed.md
+++ b/changelog/4152.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4153.fixed.md
+++ b/changelog/4153.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4154.removed.md
+++ b/changelog/4154.removed.md
@@ -1 +0,0 @@
- Removed `SambaNovaSTTService`. SambaNova no longer offers speech-to-text audio models. Use another STT provider instead.
--- a/changelog/4156.added.md
+++ b/changelog/4156.added.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4156.changed.md
+++ b/changelog/4156.changed.md
@@ -1 +0,0 @@
- ⚠️ Bumped `mem0ai` dependency from `~=0.1.94` to `>=1.0.8,<2`. Users of the `mem0` extra will need to update their mem0ai package.
--- a/changelog/4156.fixed.2.md
+++ b/changelog/4156.fixed.2.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4156.fixed.md
+++ b/changelog/4156.fixed.md
@@ -1 +0,0 @@
- `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.
--- a/changelog/4161.fixed.md
+++ b/changelog/4161.fixed.md
@@ -1 +0,0 @@
- Added missing `on_dtmf_event` callback to `LemonSliceTransportClient.setup()` `DailyCallbacks` construction, fixing a `ValidationError` at pipeline setup time.
--- a/changelog/4167.fixed.2.md
+++ b/changelog/4167.fixed.2.md
@@ -1 +0,0 @@
- Fixed an issue in `InworldTTSService` where, in cases of fast interruption, we would continue receiving audio from the previous context.
--- a/changelog/4167.fixed.md
+++ b/changelog/4167.fixed.md
@@ -1 +0,0 @@
- Fixed a word timestamp interleaving issue in `InworldTTSService` when processing multiple sentences.
--- a/changelog/4172.fixed.md
+++ b/changelog/4172.fixed.md
@@ -1 +0,0 @@
- 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.
--- a/changelog/4172.performance.md
+++ b/changelog/4172.performance.md
@@ -1 +0,0 @@
- `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.
--- a/changelog/4174.fixed.md
+++ b/changelog/4174.fixed.md
@@ -1 +0,0 @@
- ⚠️ 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.
--- a/changelog/4178.fixed.md
+++ b/changelog/4178.fixed.md
@@ -1 +0,0 @@
- Fixed timed frames (e.g. word-boundary events) arriving out of order or too late relative to TTS audio playback. When a `TTSStoppedFrame` carries a presentation timestamp, the clock queue now flushes all pending timed frames immediately once the audio task finishes sending the preceding audio, ensuring timed events always reach downstream processors before the stop signal.
--- a/env.example
+++ b/env.example
@@ -80,9 +80,15 @@ GOOGLE_TEST_CREDENTIALS=...
 # Gradium
 GRAPDIUM_API_KEY=...

+# Grok
+GROK_API_KEY=...
+
 # Groq
 GROQ_API_KEY=...

+# Hathora
+HATHORA_API_KEY=...
+
 # Heygen
 HEYGEN_API_KEY=...
 HEYGEN_LIVE_AVATAR_API_KEY=...
@@ -102,10 +108,6 @@ KRISP_VIVA_API_KEY=...
 KRISP_VIVA_FILTER_MODEL_PATH=...
 KRISP_VIVA_TURN_MODEL_PATH=...

-# LemonSlice
-LEMONSLICE_API_KEY=...
-LEMONSLICE_AGENT_ID=...
-
 # LiveKit
 LIVEKIT_API_KEY=...
 LIVEKIT_API_SECRET=...
@@ -124,9 +126,6 @@ MISTRAL_API_KEY=...
 # Neuphonic
 NEUPHONIC_API_KEY=...

-# Novita
-NOVITA_API_KEY=...
-
 # NVIDIA
 NVIDIA_API_KEY=...

@@ -176,9 +175,6 @@ 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 +208,3 @@ WHATSAPP_TOKEN=...
 WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
 WHATSAPP_PHONE_NUMBER_ID=...
 WHATSAPP_APP_SECRET=...
-
-# xAI / Grok
-XAI_API_KEY=...
--- a/examples/foundational/01-say-one-thing-piper.py
+++ b/examples/foundational/01-say-one-thing-piper.py
@@ -39,9 +39,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    # 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,
+            base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
        )

        task = PipelineTask(
--- a/examples/foundational/01-say-one-thing-rime.py
+++ b/examples/foundational/01-say-one-thing-rime.py
@@ -39,10 +39,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async with aiohttp.ClientSession() as session:
        tts = RimeHttpTTSService(
            api_key=os.getenv("RIME_API_KEY", ""),
+            voice_id="rex",
            aiohttp_session=session,
-            settings=RimeHttpTTSService.Settings(
-                voice="rex",
-            ),
        )

        task = PipelineTask(
--- a/examples/foundational/01-say-one-thing.py
+++ b/examples/foundational/01-say-one-thing.py
@@ -37,9 +37,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

    task = PipelineTask(
--- a/examples/foundational/01a-local-audio.py
+++ b/examples/foundational/01a-local-audio.py
@@ -29,9 +29,7 @@ async def main():

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

    pipeline = Pipeline([tts, transport.output()])
--- a/examples/foundational/01b-livekit-audio.py
+++ b/examples/foundational/01b-livekit-audio.py
@@ -37,9 +37,7 @@ async def main():

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

    runner = PipelineRunner()
--- a/examples/foundational/02-llm-say-one-thing.py
+++ b/examples/foundational/02-llm-say-one-thing.py
@@ -39,17 +39,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
-        ),
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
+        }
+    ]

    task = PipelineTask(
        Pipeline([llm, tts, transport.output()]),
@@ -59,9 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    # 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):
-        context = LLMContext()
-        context.add_message({"role": "developer", "content": "Say hello to the world."})
-        await task.queue_frames([LLMContextFrame(context), EndFrame()])
+        await task.queue_frames([LLMContextFrame(LLMContext(messages)), EndFrame()])

    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

--- a/examples/foundational/03-still-frame.py
+++ b/examples/foundational/03-still-frame.py
@@ -45,9 +45,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    # Create an HTTP session
    async with aiohttp.ClientSession() as session:
        imagegen = FalImageGenService(
-            settings=FalImageGenService.Settings(
-                image_size="square_hd",
-            ),
+            params=FalImageGenService.InputParams(image_size="square_hd"),
            aiohttp_session=session,
            key=os.getenv("FAL_KEY"),
        )
--- a/examples/foundational/03a-local-still-frame.py
+++ b/examples/foundational/03a-local-still-frame.py
@@ -37,9 +37,7 @@ async def main():
        )

        imagegen = FalImageGenService(
-            settings=FalImageGenService.Settings(
-                image_size="square_hd",
-            ),
+            params=FalImageGenService.InputParams(image_size="square_hd"),
            aiohttp_session=session,
            key=os.getenv("FAL_KEY"),
        )
--- a/examples/foundational/04-transports-small-webrtc.py
+++ b/examples/foundational/04-transports-small-webrtc.py
@@ -67,19 +67,19 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
-        ),
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))

-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -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."}
-        )
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/04a-transports-daily.py
+++ b/examples/foundational/04a-transports-daily.py
@@ -50,19 +50,19 @@ async def main():

        tts = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
-            settings=CartesiaTTSService.Settings(
-                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            ),
+            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
        )

-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
-            ),
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

-        context = LLMContext()
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = LLMContext(messages)
        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
            context,
            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -91,9 +91,7 @@ async def main():
        async def on_first_participant_joined(transport, participant):
            await transport.capture_participant_transcription(participant["id"])
            # Kick off the conversation.
-            context.add_message(
-                {"role": "developer", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
            await task.queue_frames([LLMRunFrame()])

        @transport.event_handler("on_participant_left")
--- a/examples/foundational/04b-transports-livekit.py
+++ b/examples/foundational/04b-transports-livekit.py
@@ -55,21 +55,24 @@ async def main():

    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))

-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
-        ),
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. "
+            "Your goal is to demonstrate your capabilities in a succinct way. "
+            "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
+            "Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
--- a/Show More
+++ b/Show More
				`@@ -0,0 +1 @@`
				- Added `TextAggregationMetricsData` metric measuring the time from the first LLM token to the first complete sentence, representing the latency cost of sentence aggregation in the TTS pipeline.
				`@@ -0,0 +1 @@`
				- Added `text_aggregation_mode` parameter to `TTSService` and all TTS subclasses with a new `TextAggregationMode` enum (`SENTENCE`, `TOKEN`). All text now flows through text aggregators regardless of mode, enabling pattern detection and tag handling in TOKEN mode.
				`@@ -0,0 +1 @@`
				- ⚠️ Deprecated `aggregate_sentences` parameter on `TTSService` and all TTS subclasses. Use `text_aggregation_mode=TextAggregationMode.SENTENCE` or `text_aggregation_mode=TextAggregationMode.TOKEN` instead.
				`@@ -0,0 +1 @@`
				- ⚠️ Refactored runtime-updatable service settings to use strongly-typed classes (`TTSSettings`, `STTSettings`, `LLMSettings`, and service-specific subclasses) instead of plain dicts. Each service's `_settings` now holds these strongly-typed objects. For service maintainers, see changes in COMMUNITY_INTEGRATIONS.md.
				`@@ -0,0 +1 @@`
				- Dict-based `UpdateSettingsFrame(settings={...})` is deprecated in favor of passing typed settings delta objects with `UpdateSettingsFrame(delta={...})`.
				`@@ -0,0 +1 @@`
				- Switched `GradiumTTSService` from `InterruptibleWordTTSService` to `AudioContextWordTTSService`, eliminating websocket disconnect/reconnect on every interruption by using `client_req_id`-based multiplexing.
				`@@ -0,0 +1 @@`
				- Word timestamp support has been moved from `WordTTSService` into `TTSService` via a new `supports_word_timestamps` parameter. Services that previously extended `WordTTSService`, `AudioContextWordTTSService`, or `WebsocketWordTTSService` now pass `supports_word_timestamps=True` to their parent `__init__` instead.
				`@@ -0,0 +1 @@`
				- Fixed Poetry compatibility by inlining `local-smart-turn-v3` dependencies (`transformers`, `onnxruntime`) into core dependencies instead of using a self-referential extra.
				`@@ -0,0 +1 @@`
				- Removed `local-smart-turn-v3` optional extra from `pyproject.toml`. The `transformers` and `onnxruntime` packages are now always installed as core dependencies since they are required by the default turn stop strategy, `TurnAnalyzerUserTurnStopStrategy` which uses `LocalSmartTurnAnalyzerV3`.
				`@@ -0,0 +1 @@`
				- Added `output_medium` parameter to `AgentInputParams` and `OneShotInputParams` in Ultravox service to control initial output medium (text or voice) at call creation time.