Semantic Live Caption: annotate a speech transcript

A Chinese and English caption interface combines streaming speech recognition with Jev judgments for important statements, emotion and communicative intent. Partial captions receive provisional annotations, followed by another judgment when the sentence closes.

Notes

Jev fans out typed questions over the transcript, and local confidence, probability-margin and Noul thresholds decide which labels to display. Optional DeepSeek calls suggest new label categories for the user to accept or ignore.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Availability & demo checks

Report a problem →

Filed under

• #voice
• #classification
• #decision-making
• #observability

In collections

• Interfaces & creative workflows →