wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Fish Audio default model to s1

Browse Source 
Update default model from speech-1.5 to s1 for Fish Audio TTS service
This commit is contained in:
Kyle Cui
2025-11-26 01:50:38 -08:00
committed by GitHub
parent 2607699664
commit 7fa0cbf2a9
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/pipecat/services/fish/tts.py
View File

@@ -76,7 +76,7 @@ class FishAudioTTSService(InterruptibleTTSService):
api_key: str,
reference_id: Optional[str] = None, # This is the voice ID
model: Optional[str] = None, # Deprecated
model_id: str = "speech-1.5",
model_id: str = "s1",
output_format: FishAudioOutputFormat = "pcm",
sample_rate: Optional[int] = None,
params: Optional[InputParams] = None,
@@ -93,7 +93,7 @@ class FishAudioTTSService(InterruptibleTTSService):
The `model` parameter is deprecated and will be removed in version 0.1.0.
Use `reference_id` instead to specify the voice model.
model_id: Specify which Fish Audio TTS model to use (e.g. "speech-1.5")
model_id: Specify which Fish Audio TTS model to use (e.g. "s1")
output_format: Audio output format. Defaults to "pcm".
sample_rate: Audio sample rate. If None, uses default.
params: Additional input parameters for voice customization.