Update SpeechmaticsSTTService to use the python voice SDK

This commit is contained in:
Sam Sykes
2025-12-20 01:59:18 +01:00
committed by GitHub
parent 5c779abad2
commit 76bae6e699
7 changed files with 715 additions and 880 deletions

View File

@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
4. Text-to-Speech (TTS)
- Low latency streaming audio synthesis
- Multiple voice options available including `sarah`, `theo`, and `megan`
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
5. Configuration Options
- `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
@@ -92,10 +92,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
language=Language.EN,
enable_vad=True,
enable_diarization=True,
focus_speakers=["S1"],
end_of_utterance_silence_trigger=0.5,
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
# focus_speakers=["S1"],
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
),

View File

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
TTS Features:
- Low latency streaming audio synthesis
- Multiple voice options available including `sarah`, `theo`, and `megan`
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
For more information:
- STT: https://docs.speechmatics.com/rt-api-ref
@@ -83,8 +83,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
language=Language.EN,
enable_diarization=True,
end_of_utterance_silence_trigger=0.5,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),
)

View File

@@ -68,7 +68,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
language=Language.EN,
enable_diarization=True,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),
)