Open-source speech-to-speech cuts voice agent history to exactly what you heard on interrupt
andimarafioti · x · 2026-11-18
The open-source speech-to-speech project (13.7k stars) by Hugging Face fixes a subtle voice agent issue: agents generate text faster than they speak, so interrupting one makes the model assume you heard the full reply. The new update trims the model's chat history to exactly what the user actually heard.
The project runs entirely locally with a default pipeline of Silero VAD → Parakeet TDT → Qwen3.5-4B → Qwen3-TTS — one command to start, no API key or cloud service needed.
More from coding & agent
- Probabl lays out 6 agent reliability terms every data scientist should know — GaelVaroquaux · 2026-11-18
- OTel Node.js SDK lands 1-line change: Object.keys swap gives 2.4x speedup — DanielLockyer · 2026-11-18
- Raycast Launches Local MCP Server So Claude, Codex and Cursor Can Drive Your Mac — dean_rie · 2026-11-18
- Academic Research Skills for Claude Code hits 57.5k GitHub stars — adnan_hashmi · 2026-11-18
- Google paper: gated self-improving agent harnesses cut token cost 10x and transfer across models — omarsar0 · 2026-11-18
- mcp-mock: deterministic open-source mock MCP server for testing clients and agents — OkSkirt1039 · 2026-11-18