Prasanna721 65cbb5613c feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) ... 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		2026-01-19 11:38:31 -08:00
..
pipecat.mdx	feat(pipecat-sdk): add speech-to-speech model support (Gemini Live)	2026-01-19 11:38:31 -08:00