dv-pipecat-ai 0.0.85.dev830__py3-none-any.whl → 0.0.85.dev831__py3-none-any.whl

{dv_pipecat_ai-0.0.85.dev830.dist-info → dv_pipecat_ai-0.0.85.dev831.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.85.dev830
+Version: 0.0.85.dev831
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.85.dev830.dist-info → dv_pipecat_ai-0.0.85.dev831.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dv_pipecat_ai-0.0.85.dev830.dist-info/licenses/LICENSE,sha256=DWY2QGf2eMCFhuu2ChairtT6CB7BEFffNVhXWc4Od08,1301
+dv_pipecat_ai-0.0.85.dev831.dist-info/licenses/LICENSE,sha256=DWY2QGf2eMCFhuu2ChairtT6CB7BEFffNVhXWc4Od08,1301
 pipecat/__init__.py,sha256=j0Xm6adxHhd7D06dIyyPV_GlBYLlBnTAERVvD_jAARQ,861
 pipecat/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pipecat/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -205,7 +205,7 @@ pipecat/services/azure/realtime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm
 pipecat/services/azure/realtime/llm.py,sha256=MnDiw-YJP3kll1gbkta4z4vsWfWZ5oBprZCinMP9O0M,2385
 pipecat/services/cartesia/__init__.py,sha256=vzh0jBnfPwWdxFfV-tu0x1HFoOTgr9s91GYmD-CJUtY,284
 pipecat/services/cartesia/stt.py,sha256=00k9gQYo_xPKb-RRJ-RNV4LPFw-7xXiFU7ACFLYttWY,12388
-pipecat/services/cartesia/tts.py,sha256=EdpVJoDhZn7N5hj-VDsCaO-W2MsA78UzOdrHR4G7w08,24355
+pipecat/services/cartesia/tts.py,sha256=Fh6hm5AUj2rNX8J4UOjHA7uAPIGcie1Dyxv5WBvV1OY,26279
 pipecat/services/cerebras/__init__.py,sha256=5zBmqq9Zfcl-HC7ylekVS5qrRedbl1mAeEwUT-T-c_o,259
 pipecat/services/cerebras/llm.py,sha256=-yzSe_6YDGigwzES-LZS4vNXMPugmvsIYEpTySyr5nA,3047
 pipecat/services/deepgram/__init__.py,sha256=IjRtMI7WytRDdmYVpk2qDWClXUiNgdl7ZkvEAWg1eYE,304
@@ -415,7 +415,7 @@ pipecat/utils/tracing/service_decorators.py,sha256=fwzxFpi8DJl6BJbK74G0UEB4ccMJg
 pipecat/utils/tracing/setup.py,sha256=7TEgPNpq6M8lww8OQvf0P9FzYc5A30xICGklVA-fua0,2892
 pipecat/utils/tracing/turn_context_provider.py,sha256=ikon3plFOx0XbMrH6DdeHttNpb-U0gzMZIm3bWLc9eI,2485
 pipecat/utils/tracing/turn_trace_observer.py,sha256=dma16SBJpYSOE58YDWy89QzHyQFc_9gQZszKeWixuwc,9725
-dv_pipecat_ai-0.0.85.dev830.dist-info/METADATA,sha256=wPJAPffJo_L5wKNWKbIxlaBG09JAGKUTFl_qkLwmoPw,32924
-dv_pipecat_ai-0.0.85.dev830.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dv_pipecat_ai-0.0.85.dev830.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
-dv_pipecat_ai-0.0.85.dev830.dist-info/RECORD,,
+dv_pipecat_ai-0.0.85.dev831.dist-info/METADATA,sha256=5ahEs864DAPIEEiiv7-7Oa-vRhRN1Ede341NuqED3Sw,32924
+dv_pipecat_ai-0.0.85.dev831.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dv_pipecat_ai-0.0.85.dev831.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
+dv_pipecat_ai-0.0.85.dev831.dist-info/RECORD,,

pipecat/services/cartesia/tts.py

@@ -15,7 +15,6 @@ from typing import AsyncGenerator, List, Literal, Optional, Union
 from loguru import logger
 from pydantic import BaseModel, Field
 
-
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
@@ -49,6 +48,26 @@ except ModuleNotFoundError as e:
     raise Exception(f"Missing module: {e}")
 
 
+class GenerationConfig(BaseModel):
+    """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.
 
@@ -102,16 +121,20 @@ 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,
@@ -120,7 +143,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
         voice_id: str,
         cartesia_version: str = "2025-04-16",
         url: str = "wss://api.cartesia.ai/tts/websocket",
-        model: str = "sonic-2",
+        model: str = "sonic-3",
         sample_rate: Optional[int] = None,
         encoding: str = "pcm_s16le",
         container: str = "raw",
@@ -136,7 +159,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
             voice_id: ID of the voice to use for synthesis.
             cartesia_version: API version string for Cartesia service.
             url: WebSocket URL for Cartesia TTS API.
-            model: TTS model to use (e.g., "sonic-2").
+            model: TTS model to use (e.g., "sonic-3").
             sample_rate: Audio sample rate. If None, uses default.
             encoding: Audio encoding format.
             container: Audio container format.
@@ -180,6 +203,7 @@ 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)
@@ -298,6 +322,11 @@ class CartesiaTTSService(AudioContextWordTTSService):
         if self._settings["speed"]:
             msg["speed"] = self._settings["speed"]
 
+        if self._settings["generation_config"]:
+            msg["generation_config"] = self._settings["generation_config"].model_dump(
+                exclude_none=True
+            )
+
         return json.dumps(msg)
 
     async def start(self, frame: StartFrame):
@@ -419,7 +448,6 @@ class CartesiaTTSService(AudioContextWordTTSService):
                 logger.error(f"{self} error: {msg}")
                 await self.push_frame(TTSStoppedFrame())
                 await self.stop_all_metrics()
-
                 await self.push_error(ErrorFrame(f"{self} error: {msg['error']}"))
                 self._context_id = None
             else:
@@ -484,23 +512,27 @@ 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,
         *,
         api_key: str,
         voice_id: str,
-        model: str = "sonic-2",
+        model: str = "sonic-3",
         base_url: str = "https://api.cartesia.ai",
         cartesia_version: str = "2024-11-13",
         sample_rate: Optional[int] = None,
@@ -514,7 +546,7 @@ class CartesiaHttpTTSService(TTSService):
         Args:
             api_key: Cartesia API key for authentication.
             voice_id: ID of the voice to use for synthesis.
-            model: TTS model to use (e.g., "sonic-2").
+            model: TTS model to use (e.g., "sonic-3").
             base_url: Base URL for Cartesia HTTP API.
             cartesia_version: API version string for Cartesia service.
             sample_rate: Audio sample rate. If None, uses default.
@@ -541,6 +573,7 @@ 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)
@@ -634,6 +667,11 @@ class CartesiaHttpTTSService(TTSService):
             if self._settings["speed"]:
                 payload["speed"] = self._settings["speed"]
 
+            if self._settings["generation_config"]:
+                payload["generation_config"] = self._settings["generation_config"].model_dump(
+                    exclude_none=True
+                )
+
             yield TTSStartedFrame()
 
             session = await self._client._get_session()