No captions to pull from because it's your own recording? Speech-to-text handles it directly — no export step needed first.
Built for personal recordings, meetings, and footage that never had subtitles to begin with.
MOV, WebM, and other common video formats work the same way.
Processed in chunks, so multi-hour recordings don't time out or fail.
Save the resulting transcript as TXT, Markdown, or PDF.
The file is processed to extract audio and transcribe it; it isn't kept or shared beyond generating your transcript.
MOV, WebM, and other common formats are supported the same way, since audio is extracted before transcription.
Files are processed in chunks, so multi-hour recordings like lectures or meetings are supported.