chicogong/ffvoice-engine

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

3Stars on the repository
2Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

chicogong/ffvoice-engine

Skill Claude CodeCodex

Offline speech-to-text and speaker diarization with the ffvoice engine. Use when the user wants to transcribe an audio file, generate subtitles (SRT/VTT/JSON), identify who spoke when (speaker diarization), caption or transcribe live microphone input, or list audio input devices — all fully on-device, with no cloud…

3 3mo ago A 78 tokens original MIT