diff --git a/changelog/3697.changed.md b/changelog/3697.changed.md new file mode 100644 index 000000000..ce7bf49d7 --- /dev/null +++ b/changelog/3697.changed.md @@ -0,0 +1 @@ +- Update `SonioxSTTService` default model to `stt-rt-v4`. \ No newline at end of file diff --git a/examples/foundational/07za-interruptible-soniox.py b/examples/foundational/07za-interruptible-soniox.py index 95677c045..b896a43b9 100644 --- a/examples/foundational/07za-interruptible-soniox.py +++ b/examples/foundational/07za-interruptible-soniox.py @@ -24,7 +24,8 @@ from pipecat.runner.types import RunnerArguments from pipecat.runner.utils import create_transport from pipecat.services.cartesia.tts import CartesiaTTSService from pipecat.services.openai.llm import OpenAILLMService -from pipecat.services.soniox.stt import SonioxSTTService +from pipecat.services.soniox.stt import SonioxInputParams, SonioxSTTService +from pipecat.transcriptions.language import Language from pipecat.transports.base_transport import BaseTransport, TransportParams from pipecat.transports.daily.transport import DailyParams from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams @@ -52,6 +53,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): stt = SonioxSTTService( api_key=os.getenv("SONIOX_API_KEY"), + vad_force_turn_endpoint=True, + params=SonioxInputParams( + language_hints=[Language.EN], + language_hints_strict=True, + ), ) tts = CartesiaTTSService( diff --git a/src/pipecat/services/soniox/stt.py b/src/pipecat/services/soniox/stt.py index 268e34508..e3e9e3e5c 100644 --- a/src/pipecat/services/soniox/stt.py +++ b/src/pipecat/services/soniox/stt.py @@ -93,7 +93,7 @@ class SonioxInputParams(BaseModel): client_reference_id: Client reference ID to use for transcription. """ - model: str = "stt-rt-preview" + model: str = "stt-rt-v4" audio_format: Optional[str] = "pcm_s16le" num_channels: Optional[int] = 1