Speech to text
Meetings, podcasts, captions, notes — plus formats, languages, and what to do when a file fails.
Each tool page is a different job. Speech to text is the workflow. vs Whisper is the model choice. Demo is a finished transcript. API is how you call the same model from your app.
Meetings, podcasts, captions, notes — plus formats, languages, and what to do when a file fails.
Word error, speakers, and price on one page, with clips. Not a generic “AI vs AI” essay.
Read a labeled sample first, or send a Bearer token. Failed API jobs are not charged.
Audio passes through our Cloudflare Worker and a contracted speech-processing service. We do not keep a permanent media library. Details are on the privacy page.