| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Windows temporal bug fix | Prasanna721 | 2026-01-19 | 1 | -2/+2 |
| | | |||||
| * | feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) | Prasanna721 | 2026-01-19 | 3 | -162/+187 |
| | | | | | | | | | Summary: - Speech-to-speech support - Auto-detect audio frames and inject memories to system prompt for native audio models (Gemini Live, etc.) - Fix memory bloating - Replace memories each turn using XML tags instead of accumulating - Add temporal context - Show recency on search results ([2d ago], [15 Jan]) - New inject_mode param - auto (default), system, or user | ||||
| * | docs changes (#678) | Dhravya Shah | 2026-01-18 | 1 | -8/+17 |
| | | | | Co-authored-by: Claude Opus 4.5 <[email protected]> | ||||
| * | pipecat-sdk (#663) | Prasanna | 2026-01-10 | 8 | -0/+856 |