From 31d084eb7803874b1e540a8f594e2e92a5e6f219 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Mon, 2 Jun 2025 13:29:05 -0400 Subject: [PATCH] Reverting Gemini Live model back to gemini-2.0-flash-live-001 --- CHANGELOG.md | 5 +++++ src/pipecat/services/gemini_multimodal_live/gemini.py | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 3c07f2e37..3d93a79ae 100644 --- a/CHANGELOG.md +++ b/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 diff --git a/src/pipecat/services/gemini_multimodal_live/gemini.py b/src/pipecat/services/gemini_multimodal_live/gemini.py index 894e53285..7ecf7e442 100644 --- a/src/pipecat/services/gemini_multimodal_live/gemini.py +++ b/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,