diff options
| author | Prasanna721 <[email protected]> | 2026-01-21 03:58:26 +0000 |
|---|---|---|
| committer | Prasanna721 <[email protected]> | 2026-01-21 03:58:26 +0000 |
| commit | 0a8c5fa0497754731cf8ff97eb0f503aaabfc97a (patch) | |
| tree | d8c583febd32a98b7510a70075adf521f7fba724 /apps/browser-extension/utils | |
| parent | feat: mobile responsive, lint formats, toast, render issue fix (#688) (diff) | |
| download | supermemory-pipecat-update.tar.xz supermemory-pipecat-update.zip | |
Re - feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) (#683)pipecat-update
#### 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
Diffstat (limited to 'apps/browser-extension/utils')
0 files changed, 0 insertions, 0 deletions