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

Merge pull request #3101 from hwuiwon/hw/inworld-talking-speed

Browse Source 
feat: Add speaking rate control to Inworld TTS service.
This commit is contained in:
Mark Backman
2025-11-20 09:50:55 -05:00
committed by GitHub
parent 51bdd8b728 ead361f665
commit ab58f72322
2 changed files with 17 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
CHANGELOG.md
View File

@@ -24,6 +24,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Added word-level timestamps support to Hume TTS service - Added word-level timestamps support to Hume TTS service
- Added optional speaking rate control to `InworldTTSService`.
### Changed ### Changed
- ⚠️ Breaking change: `LLMContext.create_image_message()`, - ⚠️ Breaking change: `LLMContext.create_image_message()`,
@@ -89,6 +91,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Prevented `HeyGenVideoService` from automatically disconnecting after 5 minutes. - Prevented `HeyGenVideoService` from automatically disconnecting after 5 minutes.
- Fixed `InworldTTSService` audio config payload to use camelCase keys expected
by the Inworld API.
## [0.0.94] - 2025-11-10 ## [0.0.94] - 2025-11-10
### Changed ### Changed

19
src/pipecat/services/inworld/tts.py
View File

@@ -146,6 +146,8 @@ class InworldTTSService(TTSService):
Parameters: Parameters:
temperature: Voice temperature control for synthesis variability (e.g., 1.1). temperature: Voice temperature control for synthesis variability (e.g., 1.1).
Valid range: [0, 2]. Higher values increase variability. Valid range: [0, 2]. Higher values increase variability.
speaking_rate: Speaking speed control (range: [0.5, 1.5]). Defaults to 1.0 when
unset.
Note: Note:
Language is automatically inferred from the input text by Inworld's TTS models, Language is automatically inferred from the input text by Inworld's TTS models,
@@ -153,6 +155,7 @@ class InworldTTSService(TTSService):
""" """
temperature: Optional[float] = None # optional temperature control (range: [0, 2]) temperature: Optional[float] = None # optional temperature control (range: [0, 2])
speaking_rate: Optional[float] = None # optional speaking rate control (range: [0.5, 1.5])
def __init__( def __init__(
self, self,
@@ -198,6 +201,7 @@ class InworldTTSService(TTSService):
- Other formats as supported by Inworld API - Other formats as supported by Inworld API
params: Optional input parameters for additional configuration. Use this to specify: params: Optional input parameters for additional configuration. Use this to specify:
- temperature: Voice temperature control for variability (range: [0, 2], e.g., 1.1, optional) - temperature: Voice temperature control for variability (range: [0, 2], e.g., 1.1, optional)
- speaking_rate: Set desired speaking speed (range: [0.5, 1.5], optional)
Language is automatically inferred from input text. Language is automatically inferred from input text.
**kwargs: Additional arguments passed to the parent TTSService class. **kwargs: Additional arguments passed to the parent TTSService class.
@@ -228,15 +232,18 @@ class InworldTTSService(TTSService):
self._settings = { self._settings = {
"voiceId": voice_id, # Voice selection from direct parameter "voiceId": voice_id, # Voice selection from direct parameter
"modelId": model, # TTS model selection from direct parameter "modelId": model, # TTS model selection from direct parameter
"audio_config": { # Audio format configuration "audioConfig": { # Audio format configuration
"audio_encoding": encoding, # Format: LINEAR16, MP3, etc. "audioEncoding": encoding, # Format: LINEAR16, MP3, etc.
"sample_rate_hertz": 0, # Will be set in start() from parent service "sampleRateHertz": 0, # Will be set in start() from parent service
}, },
} }
# Add optional temperature parameter if provided (valid range: [0, 2]) # Add optional temperature parameter if provided (valid range: [0, 2])
if params and params.temperature is not None: if params and params.temperature is not None:
self._settings["temperature"] = params.temperature self._settings["temperature"] = params.temperature
# Add optional speaking rate if provided (valid range: [0.5, 1.5])
if params and params.speaking_rate is not None:
self._settings["audioConfig"]["speakingRate"] = params.speaking_rate
# Register voice and model with parent service for metrics and tracking # Register voice and model with parent service for metrics and tracking
self.set_voice(voice_id) # Used for logging and metrics self.set_voice(voice_id) # Used for logging and metrics
@@ -257,7 +264,7 @@ class InworldTTSService(TTSService):
frame: The start frame containing initialization parameters. frame: The start frame containing initialization parameters.
""" """
await super().start(frame) await super().start(frame)
self._settings["audio_config"]["sample_rate_hertz"] = self.sample_rate self._settings["audioConfig"]["sampleRateHertz"] = self.sample_rate
async def stop(self, frame: EndFrame): async def stop(self, frame: EndFrame):
"""Stop the Inworld TTS service. """Stop the Inworld TTS service.
@@ -323,9 +330,7 @@ class InworldTTSService(TTSService):
"text": text, # Text to synthesize "text": text, # Text to synthesize
"voiceId": self._settings["voiceId"], # Voice selection (Ashley, Hades, etc.) "voiceId": self._settings["voiceId"], # Voice selection (Ashley, Hades, etc.)
"modelId": self._settings["modelId"], # TTS model (inworld-tts-1) "modelId": self._settings["modelId"], # TTS model (inworld-tts-1)
"audio_config": self._settings[ "audioConfig": self._settings["audioConfig"], # Audio format settings (LINEAR16, 48kHz)
"audio_config"
], # Audio format settings (LINEAR16, 48kHz)
} }
# Add optional temperature parameter if configured (valid range: [0, 2]) # Add optional temperature parameter if configured (valid range: [0, 2])