diff --git a/src/pipecat/services/inworld/realtime/events.py b/src/pipecat/services/inworld/realtime/events.py index 6ee3f05b3..0f05ad3c0 100644 --- a/src/pipecat/services/inworld/realtime/events.py +++ b/src/pipecat/services/inworld/realtime/events.py @@ -124,7 +124,7 @@ class AudioOutput(BaseModel): Parameters: format: The format configuration for output audio. - model: The TTS model to use (e.g. "inworld-tts-1.5-max"). + model: The TTS model to use (e.g. "inworld-tts-2"). voice: The voice ID to use (e.g. "Sarah", "Clive"). """ diff --git a/src/pipecat/services/inworld/realtime/llm.py b/src/pipecat/services/inworld/realtime/llm.py index c859c42be..ea5117467 100644 --- a/src/pipecat/services/inworld/realtime/llm.py +++ b/src/pipecat/services/inworld/realtime/llm.py @@ -206,7 +206,7 @@ class InworldRealtimeLLMService(LLMService[InworldRealtimeLLMAdapter]): api_key=os.getenv("INWORLD_API_KEY"), llm_model="openai/gpt-4.1-nano", voice="Sarah", - tts_model="inworld-tts-1.5-max", + tts_model="inworld-tts-2", ) For full control over session properties (note: ``session_properties`` @@ -231,7 +231,7 @@ class InworldRealtimeLLMService(LLMService[InworldRealtimeLLMAdapter]): output=AudioOutput( format=PCMAudioFormat(rate=24000), voice="Sarah", - model="inworld-tts-1.5-max", + model="inworld-tts-2", ), ), ), @@ -269,7 +269,7 @@ class InworldRealtimeLLMService(LLMService[InworldRealtimeLLMAdapter]): Shorthand for ``session_properties.model``. voice: Voice ID for TTS output (e.g. "Sarah", "Clive"). Shorthand for ``session_properties.audio.output.voice``. - tts_model: TTS model to use (e.g. "inworld-tts-1.5-max"). + tts_model: TTS model to use (e.g. "inworld-tts-2"). Shorthand for ``session_properties.audio.output.model``. stt_model: STT model for input transcription (e.g. "assemblyai/universal-streaming-multilingual"). @@ -286,7 +286,7 @@ class InworldRealtimeLLMService(LLMService[InworldRealtimeLLMAdapter]): """ default_model = llm_model or "openai/gpt-4.1-mini" default_voice = voice or "Clive" - default_tts_model = tts_model or "inworld-tts-1.5-max" + default_tts_model = tts_model or "inworld-tts-2" default_stt_model = stt_model or "assemblyai/u3-rt-pro" default_settings = self.Settings( diff --git a/src/pipecat/services/inworld/tts.py b/src/pipecat/services/inworld/tts.py index 0e087082c..5c0194ff1 100644 --- a/src/pipecat/services/inworld/tts.py +++ b/src/pipecat/services/inworld/tts.py @@ -162,7 +162,7 @@ class InworldHttpTTSService(TTSService): """ # 1. Initialize default_settings with hardcoded defaults default_settings = self.Settings( - model="inworld-tts-1.5-max", + model="inworld-tts-2", voice="Ashley", language=None, speaking_rate=None, @@ -604,7 +604,7 @@ class InworldTTSService(WebsocketTTSService): # 1. Initialize default_settings with hardcoded defaults default_settings = self.Settings( - model="inworld-tts-1.5-max", + model="inworld-tts-2", voice="Ashley", language=None, speaking_rate=None,