diff --git a/CHANGELOG.md b/CHANGELOG.md index 6d581ccce..209c9cb11 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -33,9 +33,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - `CartesiaSTTService` now inherits from `WebsocketSTTService`. - Package upgrades: + - `openai` upgraded to support up to 2.x.x. - `openpipe` upgraded to support up to 5.x.x. +- `SpeechmaticsSTTService` updated dependencies for `speechmatics-rt>=0.5.0`. + ### Fixed - Fixed multiple pipeline task cancellation issues. `asyncio.CancelledError` is @@ -59,6 +62,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 incorrectly 16-bit aligned audio frames, potentially leading to internal errors or static audio. +- Fixed an issue in `SpeechmaticsSTTService` where `AdditionalVocabEntry` items + needed to have `sounds_like` for the session to start. + ### Other - Added foundational example `47-sentry-metrics.py`, demonstrating how to use the diff --git a/pyproject.toml b/pyproject.toml index 0d94d0fa3..65546311c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -102,7 +102,7 @@ silero = [ "onnxruntime>=1.20.1,<2" ] simli = [ "simli-ai~=0.1.10"] soniox = [ "pipecat-ai[websockets-base]" ] soundfile = [ "soundfile~=0.13.0" ] -speechmatics = [ "speechmatics-rt>=0.4.0" ] +speechmatics = [ "speechmatics-rt>=0.5.0" ] strands = [ "strands-agents>=1.9.1,<2" ] tavus=[] together = [] diff --git a/src/pipecat/services/speechmatics/stt.py b/src/pipecat/services/speechmatics/stt.py index 2c1db2a15..901edb0e8 100644 --- a/src/pipecat/services/speechmatics/stt.py +++ b/src/pipecat/services/speechmatics/stt.py @@ -620,7 +620,7 @@ class SpeechmaticsSTTService(STTService): transcription_config.additional_vocab = [ { "content": e.content, - "sounds_like": e.sounds_like, + **({"sounds_like": e.sounds_like} if e.sounds_like else {}), } for e in self._params.additional_vocab ]