Reverting Gemini Live model back to gemini-2.0-flash-live-001

CHANGELOG.md

@@ -67,6 +67,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Reverted the default model for `GeminiMultimodalLiveLLMService` back to
+  `models/gemini-2.0-flash-live-001`.
+  `gemini-2.5-flash-preview-native-audio-dialog` has inconsistent performance.
+  You can opt in to using this model by setting the `model` arg.
+
 - Function calls are now cancelled by default if there's an interruption. To
   disable this behavior you can set `cancel_on_interruption=False` when
   registering the function call. Since function calls are executed as tasks you

src/pipecat/services/gemini_multimodal_live/gemini.py

@@ -336,7 +336,7 @@ class GeminiMultimodalLiveLLMService(LLMService):
         *,
         api_key: str,
         base_url: str = "generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent",
-        model="models/gemini-2.5-flash-preview-native-audio-dialog",
+        model="models/gemini-2.0-flash-live-001",
         voice_id: str = "Charon",
         start_audio_paused: bool = False,
         start_video_paused: bool = False,