FishTTSService: deprecate model, add reference_id

This commit is contained in:
Mark Backman
2025-07-03 12:56:24 -07:00
parent 8f6544efe2
commit 251ea756c8
2 changed files with 39 additions and 18 deletions

View File

@@ -61,8 +61,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Added `session_token` parameter to `AWSNovaSonicLLMService`.
- Added Gemini Multimodal Live File API for uploading, fetching, listing, and
deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
- Added Gemini Multimodal Live File API for uploading, fetching, listing, and
deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
### Changed
@@ -75,7 +75,7 @@ deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
### Fixed
- Fixed an issue where audio would get stuck in the queue when an interrupt occurs
- Fixed an issue where audio would get stuck in the queue when an interrupt occurs
during Azure TTS synthesis.
- Fixed a race condition that occurs in Python 3.10+ where the task could miss
@@ -83,6 +83,12 @@ deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
- Fixed a `AWSNovaSonicLLMService` issue introduced in 0.0.72.
### Deprecated
- In `FishTTSService`, deprecated `model` and replaced with `reference_id`.
This change is to better align with Fish Audio's variable naming and to
reduce confusion about what functionality the variable controls.
## [0.0.73] - 2025-06-26
### Fixed

View File

@@ -71,7 +71,8 @@ class FishAudioTTSService(InterruptibleTTSService):
self,
*,
api_key: str,
model: str, # This is the reference_id
reference_id: Optional[str] = None, # This is the voice ID
model: Optional[str] = None, # Deprecated
output_format: FishAudioOutputFormat = "pcm",
sample_rate: Optional[int] = None,
params: Optional[InputParams] = None,
@@ -81,7 +82,13 @@ class FishAudioTTSService(InterruptibleTTSService):
Args:
api_key: Fish Audio API key for authentication.
model: Reference ID of the voice model to use for synthesis.
reference_id: Reference ID of the voice model to use for synthesis.
model: Deprecated. Reference ID of the voice model to use for synthesis.
.. deprecated:: 0.0.74
The `model` parameter is deprecated and will be removed in version 0.1.0.
Use `reference_id` instead to specify the voice model.
output_format: Audio output format. Defaults to "pcm".
sample_rate: Audio sample rate. If None, uses default.
params: Additional input parameters for voice customization.
@@ -96,6 +103,26 @@ class FishAudioTTSService(InterruptibleTTSService):
params = params or FishAudioTTSService.InputParams()
# Validation for model and reference_id parameters
if model and reference_id:
raise ValueError(
"Cannot specify both 'model' and 'reference_id'. Use 'reference_id' only."
)
if model is None and reference_id is None:
raise ValueError("Must specify 'reference_id' (or deprecated 'model') parameter.")
if model:
import warnings
warnings.warn(
"Parameter 'model' is deprecated and will be removed in a future version. "
"Use 'reference_id' instead.",
DeprecationWarning,
stacklevel=2,
)
reference_id = model
self._api_key = api_key
self._base_url = "wss://api.fish.audio/v1/tts/live"
self._websocket = None
@@ -111,11 +138,9 @@ class FishAudioTTSService(InterruptibleTTSService):
"speed": params.prosody_speed,
"volume": params.prosody_volume,
},
"reference_id": model,
"reference_id": reference_id,
}
self.set_model_name(model)
def can_generate_metrics(self) -> bool:
"""Check if this service can generate processing metrics.
@@ -124,16 +149,6 @@ class FishAudioTTSService(InterruptibleTTSService):
"""
return True
async def set_model(self, model: str):
"""Set the TTS model (reference ID).
Args:
model: The reference ID of the voice model to use.
"""
self._settings["reference_id"] = model
await super().set_model(model)
logger.info(f"Switching TTS model to: [{model}]")
async def start(self, frame: StartFrame):
"""Start the Fish Audio TTS service.