Turn video speech into text and captions

Transcribes automatically on import or recording and labels speakers; you correct the text, then export captions via Publish > Export > Subtitles as SRT or VTT, or the transcript as Word, plain text, Markdown or HTML. Where it stops: Free covers 1 media hour a month; no Chinese, Japanese or Russian; one language per file.

Every upload gets automatic captions and an editable transcript in about 99 languages, shown in the player and downloadable as .srt, .vtt or .ttml. Where it stops: AI subtitle translation uses AI credits; below Enterprise only the account Owner can translate.

Auto subtitles in 100+ languages plus Edit with Script, an interactive transcript you correct like a document; it also accepts existing SRT or VTT files. Where it stops: Free includes 10 minutes of auto subtitles a month; subtitle file download and Detect Speakers need Pro.

Captions > Auto Captions turns speech into styled on-screen captions after you pick the spoken language; batch edit fixes many lines at once, and captions export as SRT or TXT. Where it stops: About 15 minutes per recognition; longer videos must be split into parts.

Recordings made in Riverside get an automatic transcript and animated captions; on Pro you download the transcript as TXT or SRT with timestamps. Where it stops: Covers only what you record there; no transcript download on Free, no transcript of screen-share audio, one speaker label per audio track.

Each upload is transcribed automatically without spending credits, and the transcript becomes captions in the Wistia player in a couple of clicks, with adjustable size, color and contrast. Where it stops: Built around the Wistia player; translation of transcripts and captions is not on Free.

When you translate a video, captions are generated automatically and export as SRT; the translated script can be proofread before the final render. Where it stops: No standalone transcription of an uploaded video; no closed captions for avatar videos.