semantic-live-caption
听写纸 · Real-time speech captions with live semantic annotation (key points / emotion / intent) — Confucius4-R2T2 + TypeSafe Jev + DeepSeek
How it uses Jev
基于 Confucius4-R2T2（网易有道开源的流式 ASR 模型）做听写，TypeSafe Jev 做逐句实时判断，可选接入 DeepSeek 自动发现新标签。适用于 会议、访谈、播客、直播、口播视频 等任何"说话→要文字稿"的场景。
- Languages
- HTML 92% · Python 5% · Shell 3%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-21
- Stars at snapshot
- 5
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.