GitHub - lonthq/overtone-captions: Captions cut for every screen shape, from one file. A caption format, a video.js plugin, and a CLI that turns audio into word-timed captions.

Hi HN, I'm Ruud, co-founder of Lont. We turn company emails into personalized videos. Video captions cost us manual work twice: fixing misheard words, then fixing layout, like lines ending on “the”. Overtone uses multiple models to listen to the audio: gpt-transcribe, Azure STT, and Elevenlabs…