来源节选（非本站原创长文，完整内容请见来源）
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 Scribe. When they return conflicting results, Overtone sends small clips to the models again, and then lets an LLM decide what was actually said.
The LLM is like a human doing a sanity check on the transcription model. Humans would easily recognize a word to be different based on context.
文章来源
github.com