Prasanna721 0a8c5fa049 Re - feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) (#683) ... #### RE-RAISING Pipecat live speech PR ### Added native speech-to-speech model support ### 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 update - Update the docs for native speech-2-speech models		2026-01-21 03:58:26 +00:00
..
ai-sdk.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
claude-memory.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
memory-graph.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
n8n.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
openai.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
pipecat.mdx	Re - feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) (#683)	2026-01-21 03:58:26 +00:00
supermemory-sdk.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00
zapier.mdx	docs changes (#678)	2026-01-18 16:55:32 -08:00