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

feat: add generation_config support for Cartesia Sonic-3

Browse Source 
Add GenerationConfig dataclass with volume, speed, and emotion parameters
for Cartesia Sonic-3 TTS models. This enables fine-grained control over
speech generation including volume (0.5-2.0), speed (0.6-1.5), and
emotion (60+ options).

Changes:
- Add GenerationConfig dataclass with proper Google-style docstrings
- Update CartesiaTTSService.InputParams to include generation_config
- Update CartesiaHttpTTSService.InputParams to include generation_config
- Modify _build_msg() to include generation_config in WebSocket messages
- Modify run_tts() to include generation_config in HTTP requests
- Maintain backward compatibility with existing speed and emotion parameters

The legacy speed (literal strings) and emotion (list) parameters remain
available for non-Sonic-3 models.
This commit is contained in:
Roshan
2025-10-28 15:10:46 -07:00
parent 4d82a1260b
commit df8aa3e4b0
1 changed files with 56 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
src/pipecat/services/cartesia/tts.py
View File

@@ -10,6 +10,7 @@ import base64
import json
import uuid
import warnings
from dataclasses import dataclass
from typing import AsyncGenerator, List, Literal, Optional, Union
from loguru import logger
@@ -48,6 +49,27 @@ except ModuleNotFoundError as e:
raise Exception(f"Missing module: {e}")
@dataclass
class GenerationConfig:
"""Configuration for Cartesia Sonic-3 generation parameters.
Sonic-3 interprets these parameters as guidance to ensure natural speech.
Test against your content for best results.
Parameters:
volume: Volume multiplier for generated speech. Valid range: [0.5, 2.0]. Default is 1.0.
speed: Speed multiplier for generated speech. Valid range: [0.6, 1.5]. Default is 1.0.
emotion: Single emotion string to guide the emotional tone. Examples include neutral,
angry, excited, content, sad, scared. Over 60 emotions are supported. For best
results, use with recommended voices: Leo, Jace, Kyle, Gavin, Maya, Tessa, Dana,
and Marian.
"""
volume: Optional[float] = None
speed: Optional[float] = None
emotion: Optional[str] = None
def language_to_cartesia_language(language: Language) -> Optional[str]:
"""Convert a Language enum to Cartesia language code.
@@ -101,16 +123,19 @@ class CartesiaTTSService(AudioContextWordTTSService):
Parameters:
language: Language to use for synthesis.
speed: Voice speed control.
emotion: List of emotion controls.
speed: Voice speed control for non-Sonic-3 models (literal values).
emotion: List of emotion controls for non-Sonic-3 models.
.. deprecated:: 0.0.68
The `emotion` parameter is deprecated and will be removed in a future version.
generation_config: Generation configuration for Sonic-3 models. Includes volume,
speed (numeric), and emotion (string) parameters.
"""
language: Optional[Language] = Language.EN
speed: Optional[Literal["slow", "normal", "fast"]] = None
emotion: Optional[List[str]] = []
generation_config: Optional[GenerationConfig] = None
def __init__(
self,
@@ -179,6 +204,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
else "en",
"speed": params.speed,
"emotion": params.emotion,
"generation_config": params.generation_config,
}
self.set_model_name(model)
self.set_voice(voice_id)
@@ -297,6 +323,17 @@ class CartesiaTTSService(AudioContextWordTTSService):
if self._settings["speed"]:
msg["speed"] = self._settings["speed"]
if self._settings["generation_config"]:
gen_config = {}
if self._settings["generation_config"].volume is not None:
gen_config["volume"] = self._settings["generation_config"].volume
if self._settings["generation_config"].speed is not None:
gen_config["speed"] = self._settings["generation_config"].speed
if self._settings["generation_config"].emotion is not None:
gen_config["emotion"] = self._settings["generation_config"].emotion
if gen_config:
msg["generation_config"] = gen_config
return json.dumps(msg)
async def start(self, frame: StartFrame):
@@ -482,16 +519,19 @@ class CartesiaHttpTTSService(TTSService):
Parameters:
language: Language to use for synthesis.
speed: Voice speed control.
emotion: List of emotion controls.
speed: Voice speed control for non-Sonic-3 models (literal values).
emotion: List of emotion controls for non-Sonic-3 models.
.. deprecated:: 0.0.68
The `emotion` parameter is deprecated and will be removed in a future version.
generation_config: Generation configuration for Sonic-3 models. Includes volume,
speed (numeric), and emotion (string) parameters.
"""
language: Optional[Language] = Language.EN
speed: Optional[Literal["slow", "normal", "fast"]] = None
emotion: Optional[List[str]] = Field(default_factory=list)
generation_config: Optional[GenerationConfig] = None
def __init__(
self,
@@ -539,6 +579,7 @@ class CartesiaHttpTTSService(TTSService):
else "en",
"speed": params.speed,
"emotion": params.emotion,
"generation_config": params.generation_config,
}
self.set_voice(voice_id)
self.set_model_name(model)
@@ -632,6 +673,17 @@ class CartesiaHttpTTSService(TTSService):
if self._settings["speed"]:
payload["speed"] = self._settings["speed"]
if self._settings["generation_config"]:
gen_config = {}
if self._settings["generation_config"].volume is not None:
gen_config["volume"] = self._settings["generation_config"].volume
if self._settings["generation_config"].speed is not None:
gen_config["speed"] = self._settings["generation_config"].speed
if self._settings["generation_config"].emotion is not None:
gen_config["emotion"] = self._settings["generation_config"].emotion
if gen_config:
payload["generation_config"] = gen_config
yield TTSStartedFrame()
session = await self._client._get_session()