mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-11-18 16:08:56 +00:00
1.5 KiB
1.5 KiB
Transcribe
Word-level timestamps for captions, or an import of an existing transcript.
Run it
hyperframes transcribe audio.mp3 --model small.en— known Englishhyperframes transcribe video.mp4 --model small --language es— known non-English; no.enmodelhyperframes transcribe subtitles.srt— import an SRT, a VTT or an OpenAI Whisper JSON responsehyperframes transcribe transcript.json --to srt— export captions;--to vttfor VTT,--outputfor the path--jsonprints the result as JSON and sends progress lines to stderr
Pick the model
- Always pass
--model. The defaultsmall.entranslates non-English audio into English. .enmodels (tiny.en,base.en,small.en,medium.en) are English only. Usesmall,mediumorlarge-v3with--languagefor anything else.- Speech over music: start with
medium.en.
Pick the engine
--engine auto(default) uses Parakeet when it is installed and covers--language, otherwise whisper--engine whisperor--engine parakeetforce one; install Parakeet withhyperframes models install parakeet--engine heygenuses HeyGen's speech model; it needs an API key and is charged to API credits.--speakerslabels each word with its speaker--no-runtime-installrefuses to install the whisper runtime;--optionalexits 0 when whisper is unavailable--timeout <ms>raises the whisper time limit on slow machines (minimum 5000)
Run hyperframes transcribe --help for every flag.