semantic-live-caption

A real-time captioning tool (documented in Chinese) that combines a streaming speech-recognition model with Jev, judging each sentence live to bold key points, color-code emotion, and stamp intent onto the transcript as it's spoken, with an optional DeepSeek integration for discovering new label categories — aimed at meetings, interviews, podcasts, and livestreams.

unverified — sourced from awesomejev.com; description independently written by AionEdge from the repo’s own GitHub metadata and README, not GitHub-API relevance-checked