diff --git a/CHANGELOG.md b/CHANGELOG.md index 209675a81..6394f744a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,11 +5,15 @@ All notable changes to **Pipecat** will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [Unreleased] +## [0.0.93] - 2025-11-07 ### Added -- Added support for passing in a `ToolsSchem` in lieu of a list of provider- +- Added support for Sarvam Speech-to-Text service (`SarvamSTTService`) with + streaming WebSocket support for `saarika` (STT) and `saaras` (STT-translate) + models. + +- Added support for passing in a `ToolsSchema` in lieu of a list of provider- specific dicts when initializing `OpenAIRealtimeLLMService` or when updating it using `LLMUpdateSettingsFrame`. @@ -116,6 +120,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 supported languages before Pipecat's service classes are updated, while still providing guidance on verified languages. +### Removed + +- Removed `needs_mcp_alternate_schema()` from `LLMService`. The mechanism that + relied on it went away. + ### Fixed - Restore backwards compatibility for vision/image features (broken in 0.0.92) @@ -139,18 +148,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Fixed `GoogleLLMService` token counting to avoid double-counting tokens when Gemini sends usage metadata across multiple streaming chunks. -### Removed - -- Removed `needs_mcp_alternate_schema()` from `LLMService`. The mechanism that - relied on it went away. - ## [0.0.92] - 2025-10-31 🎃 "The Haunted Edition" 👻 ### Added -- Added supprt for Sarvam Speech-to-Text service (`SarvamSTTService`) with streaming WebSocket - support for `saarika` (STT) and `saaras` (STT-translate) models. - - Added a new `DeepgramHttpTTSService`, which delivers a meaningful reduction in latency when compared to the `DeepgramTTSService`.