From 241a947b8b4b6d0463e5d5f6ee557df3f69a16ce Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Fri, 11 Apr 2025 11:22:03 -0400 Subject: [PATCH] Add CHANGELOG entries --- CHANGELOG.md | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index fdb16fd83..56b5da75f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,7 +9,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added -- Added support in `SmallWebRTCTransport` to detect when remote tracks are +- Added media resolution control to `GeminiMultimodalLiveLLMService` with + `GeminiMediaResolution` enum, allowing configuration of token usage for + image processing (LOW: 64 tokens, MEDIUM: 256 tokens, HIGH: zoomed reframing + with 256 tokens). + +- Added Gemini's Voice Activity Detection (VAD) configuration to + `GeminiMultimodalLiveLLMService` with `GeminiVADParams`, allowing fine + control over speech detection sensitivity and timing, including: + + - Start sensitivity (how quickly speech is detected) + - End sensitivity (how quickly turns end after pauses) + - Prefix padding (milliseconds of audio to keep before speech is detected) + - Silence duration (milliseconds of silence required to end a turn) + +- Added comprehensive language support to `GeminiMultimodalLiveLLMService`, + supporting over 30 languages via the `language` parameter, with proper + mapping between Pipecat's `Language` enum and Gemini's language codes. + +- Added support in `SmallWebRTCTransport` to detect when remote tracks are muted. - Added support for image capture from a video stream to the @@ -34,6 +52,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed +- In `GeminiMultimodalLiveLLMService`, removed the `transcribe_model_audio` + parameter in favor of Gemini Live's native output transcription support. Now + text transcriptions are produced directly by the model. No configuration is + required. + - Updated `GeminiMultimodalLiveLLMService`’s default `model` to `models/gemini-2.0-flash-live-001` and `base_url` to the `v1beta` websocket URL.