Input text with audio

[DeafNet]

I was wondering if they have input text and audio by using whisper ai and getting srt ?

[niksedk]

SE can get an srt file from audio (or video with audio)... either via Whisper or via Vosk.

Try the latest beta version here: https://github.com/SubtitleEdit/subtitleedit/releases/download/3.6.13/SubtitleEditBeta.zip
(The beta version is preferred atm, at some model links have changed - use the Purfview Faster-Whisper)

It's in the video menu:

Read more here: https://www.nikse.dk/subtitleedit/help#audio_to_text_whisper

[DeafNet]

I mean I add the breakdown text to the system and add audio so whisper can syncs into timestamp ?

[niksedk]

Whisper generates text and timestamps. SE/Whisper cannot sync an existing text.

[DeafNet]

timestamps

I mean to said exit text and audio to create from whisper in timestamp. Is this possible ?