Merge pull request #3201 from pipecat-ai/changelog-0.0.97

Release 0.0.97 - Changelog Update

CHANGELOG.md

@@ -7,6 +7,114 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- towncrier release notes start -->
 
+## [0.0.97] - 2025-12-05
+
+### Added
+
+- Added new Gradium services, `GradiumSTTService` and `GradiumTTSService`, for
+  speech-to-text and text-to-speech functionality using Gradium's API.
+
+- Additions for `AsyncAITTSService` and `AsyncAIHttpTTSService`:
+
+  - Added new `languages`: `pt`, `nl`, `ar`, `ru`, `ro`, `ja`, `he`, `hy`,
+    `tr`, `hi`, `zh`.
+  - Updated the default model to `asyncflow_multilingual_v1.0` for improved
+    accuracy and broader language coverage.
+
+- Added optional tool and tool output filters for MCP services.
+
+### Changed
+
+- Updated Deepgram logging to include Deepgram request IDs for improved
+  debugging.
+
+- Text Aggregation Improvements:
+
+  - **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
+    `AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
+    enables the aggregator to return multiple results based on the provided
+    text.
+  - Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
+    `PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
+    the base class's sentence detection logic.
+
+- Improved interruption handling to prevent bots from repeating themselves. LLM
+  services that return multiple sentences in a single response (e.g.,
+  `GoogleLLMService`) are now split into individual sentences before being sent
+  to TTS. This ensures interruptions occur at sentence boundaries, preventing
+  the bot from repeating content after being interrupted during long responses.
+
+- Updated `AICFilter` to use Quail STT as the default model
+  (`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine
+  interaction (e.g., voice agents, speech-to-text) and operates at a native
+  sample rate of 16 kHz with fixed enhancement parameters.
+
+- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is
+  called with an exception, the file name and line number where the exception
+  occured are now logged.
+
+- Updated Smart Turn model weights to v3.1.
+
+- Smart Turn analyzer now uses the full context of the turn rather than just
+  the audio since VAD last triggered.
+
+- Updated `CartesiaSTTService` to return the full transcription `result` in the
+  `TranscriptionFrame` and `InterimTranscriptionFrame`. This provides access to
+  word timestamp data.
+
+- `HumeTTSService` changes:
+
+  - Added tracking headers (`X-Hume-Client-Name` and `X-Hume-Client-Version`)
+    to all requests made by `HumeTTSService` to the Hume API for better usage
+    tracking and analytics.
+  - Added `stop()` and `cancel()` cleanup methods to `HumeTTSService` to
+    properly close the HTTP client and prevent resource leaks.
+
+### Deprecated
+
+- NVIDIA Services name changes (all functionality is unchanged):
+
+  - `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
+  - `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
+  - `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
+  - Use `uv pip install pipecat-ai[nvidia]` instead of
+    `uv pip install pipecat-ai[riva]`
+
+- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer
+  has any effect. Noise gating is now handled automatically by the AIC VAD
+  system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.
+
+- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.
+
+### Fixed
+
+- Fixed bug in `PatternPairAggregator` where pattern handlers could be called
+  multiple times for `KEEP` or `AGGREGATE` patterns.
+
+- Fixed sentence aggregation to correctly handle ambiguous punctuation in
+  streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").
+
+- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was always
+  set to `us-east-1` when providing an AWS_REGION env var.
+
+- Fixed an issue in `SarvamTTSService` where the last sentence was not being
+  spoken. Now, audio is flushed when the TTS services receives the
+  `LLMFullResponseEndFrame` or `EndFrame`.
+
+- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was
+  incorrectly pushed after a functional call. This caused an issue with the
+  voice-ui-kit's conversational panel rending of the LLM output after a
+  function call.
+
+- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM
+  services.
+
+- Fixed an issue that caused `WebsocketService` instances to attempt
+  reconnection during shutdown.
+
+- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were
+  only reported on the first TTS generation per turn.
+
 ## [0.0.96] - 2025-11-26 🦃 "Happy Thanksgiving!" 🦃
 
 ### Added

changelog/3072.changed.md

@@ -1 +0,0 @@
-- Updated Deepgram logging to include Deepgram request IDs for improved debugging.

changelog/3130.deprecated.md

@@ -1,7 +0,0 @@
-- NVIDIA Services name changes (all functionality is unchanged):
-
-  - `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
-  - `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
-  - `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
-  - Use `uv pip install pipecat-ai[nvidia]` instead of
-    `uv pip install pipecat-ai[riva]`

changelog/3132.changed.2.md

@@ -1,9 +0,0 @@
-- Text Aggregation Improvements:
-
-  - **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
-    `AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
-    enables the aggregator to return multiple results based on the provided
-    text.
-  - Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
-    `PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
-    the base class's sentence detection logic.

changelog/3132.changed.md

@@ -1 +0,0 @@
-- Improved interruption handling to prevent bots from repeating themselves. LLM services that return multiple sentences in a single response (e.g., `GoogleLLMService`) are now split into individual sentences before being sent to TTS. This ensures interruptions occur at sentence boundaries, preventing the bot from repeating content after being interrupted during long responses.

changelog/3132.fixed.2.md

@@ -1 +0,0 @@
-- Fixed bug in `PatternPairAggregator` where pattern handlers could be called multiple times for `KEEP` or `AGGREGATE` patterns.

changelog/3132.fixed.md

@@ -1 +0,0 @@
-- Fixed sentence aggregation to correctly handle ambiguous punctuation in streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").

changelog/3153.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was always set to `us-east-1` when providing an AWS_REGION env var.

changelog/3155.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue in `SarvamTTSService` where the last sentence was not being spoken. Now, audio is flushed when the TTS services receives the `LLMFullResponseEndFrame` or `EndFrame`.

changelog/3156.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was incorrectly pushed after a functional call. This caused an issue with the voice-ui-kit's conversational panel rending of the LLM output after a function call.

changelog/3162.changed.md

@@ -1 +0,0 @@
-- Updated `AICFilter` to use Quail STT as the default model (`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine interaction (e.g., voice agents, speech-to-text) and operates at a native sample rate of 16 kHz with fixed enhancement parameters.

changelog/3162.deprecated.md

@@ -1 +0,0 @@
-- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer has any effect. Noise gating is now handled automatically by the AIC VAD system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.

changelog/3168.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM services.

changelog/3176.added.md

@@ -1 +0,0 @@
-- Added new Gradium services, `GradiumSTTService` and `GradiumTTSService`, for speech-to-text and text-to-speech functionality using Gradium's API.

changelog/3176.changed.md

@@ -1 +0,0 @@
-- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is called with an exception, the file name and line number where the exception occured are now logged.

changelog/3177.changed.md

@@ -1 +0,0 @@
-- Updated Smart Turn model weights to v3.1.

changelog/3181.deprecated.md

@@ -1 +0,0 @@
-- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.

changelog/3183.changed.md

@@ -1 +0,0 @@
-- Smart Turn analyzer now uses the full context of the turn rather than just the audio since VAD last triggered.

changelog/3184.added.md

@@ -1,6 +0,0 @@
-- Additions for `AsyncAITTSService` and `AsyncAIHttpTTSService`:
-
-  - Added new `languages`: `pt`, `nl`, `ar`, `ru`, `ro`, `ja`, `he`, `hy`,
-    `tr`, `hi`, `zh`.
-  - Updated the default model to `asyncflow_multilingual_v1.0` for improved
-    accuracy and broader language coverage.

changelog/3185.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue that caused `WebsocketService` instances to attempt reconnection during shutdown.

changelog/3186.fixed.md

@@ -1 +0,0 @@
-- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were only reported on the first TTS generation per turn.

changelog/3187.added.md

@@ -1 +0,0 @@
-- Added optional tool and tool output filters for MCP services.

changelog/3192.changed.md

@@ -1 +0,0 @@
-- Updated `CartesiaSTTService` to return the full transcription `result` in the `TranscriptionFrame` and `InterimTranscriptionFrame`. This provides access to word timestamp data.

changelog/3195.changed.md

@@ -1,7 +0,0 @@
-- `HumeTTSService` changes:
-
-  - Added tracking headers (`X-Hume-Client-Name` and `X-Hume-Client-Version`)
-    to all requests made by `HumeTTSService` to the Hume API for better usage
-    tracking and analytics.
-  - Added `stop()` and `cancel()` cleanup methods to `HumeTTSService` to
-    properly close the HTTP client and prevent resource leaks.