Convert video to text, free

Upload a video and ChatCut turns its speech into an editable transcript, timed to every word. Transcription uses no credits.

Free account · MP4, MOV, WebM, MP3, WAV and more · TXT or SRT out

A video's transcript in ChatCut's Transcript panel, with the same words as captions on the video

Trusted by 400,000+ creators

How to convert video to text

Four steps in the ChatCut web app, and none of them use credits.

  1. Open ChatCut

    Sign in with Google or a one-time email code. The web app runs in your browser.

  2. Upload your video

    In My Assets, select Upload, pick a video or audio file, and drag it onto the timeline.

  3. Turn on Captions

    Select Captions in the playback controls. When transcription finishes, read the text in the Transcript panel.

  4. Export the text

    Open Export → Subtitles and choose plain text (.txt) or SubRip (.srt).

Rather not click through it? Transcribe in ChatCut opens a project where the Agent asks for your video and does the steps. Agent messages use credits.

More than a block of text

The transcript stays tied to the video, so you can fix it, cut with it, caption with it and translate it.

Fix it like a document

Click any word to jump the player there. Select a passage to edit its text, change its speaker, or delete it, which cuts that moment from the video.

How the Transcript panel works
ChatCut's Transcript panel next to the video, with captions on

Turn the text into captions

The same words become timed captions on the video. Pick a style such as Netflix or TikTok Pop, then color single words.

Add captions to your video
Styling a caption's highlight word in ChatCut

Translate the captions

Choose Translate captions and a language. The translation lands on its own track, so you can style and export it separately.

Translate captions
Original and Spanish captions shown together in ChatCut

Download TXT or SRT

Export → Subtitles saves the active caption track as plain text for notes and articles, or as an SRT file for YouTube and other players.

Export video, audio and subtitles
ChatCut's Export Settings with a Subtitles tab

What goes in, what comes out

Common video and audio files in, plain text or subtitles out.

Video in
MP4, MOV, WebM, MKV, AVI, TS
Audio in
MP3, WAV, AAC, FLAC, OGG
Text out
TXT or SRT, or captions burned into an MP4
Credits
None for transcription, captions or export

Every supported format

Subscribe to get your AI video editor

Unlock member features, models, and export allowances. Get more credits every month

$0

No credit card required

Free starter allowance

Try for free
  • Basic editing and exports
  • AI images and motion graphics
  • AI captions and music
  • AI avatars; voice cloning and previews
  • Web export limit: 60 minutes total
CodexClaudeWorkBuddy

Some features are completely free in Codex, Claude, and WorkBuddy

Learn More
$21 $25 /month 16% off

$252 · Billed annually

100 credits / month

Get started
  • Seedance 2.5 (up to 204s of video)
  • Seedance 2.0 (up to 294s of video)
  • MiniMax H3 (Up to 256s of video)
  • MiniMax H3 Max (Up to 416s of video)
  • GPT Image 2 (up to 384 images)
  • Nano Banana 2 (up to 256 images)
  • Motion graphics (up to 500 clips)
  • AI music (up to 454 songs)
  • Clone voices and reuse them in projects (up to 1 voices)
  • All AI agent editing capabilities
  • Motion graphics transparent export
  • No export limit
$38 $50 /month 24% off

$456 · Billed annually

200 credits / month

Get started
  • Seedance 2.5 (up to 408s of video)
  • Seedance 2.0 (up to 588s of video)
  • MiniMax H3 (Up to 512s of video)
  • MiniMax H3 Max (Up to 833s of video)
  • GPT Image 2 (up to 769 images)
  • Nano Banana 2 (up to 512 images)
  • Motion graphics (up to 1,000 clips)
  • AI music (up to 909 songs)
  • Clone voices and reuse them in projects (up to 2 voices)
  • All AI agent editing capabilities
  • Motion graphics transparent export
  • No export limit
$141 $200 /month 30% off

$1692 · Billed annually

800 credits / month

Get started
  • 400 credits / month
  • 800 credits / month
  • 1,200 credits / month
  • 2,000 credits / month
  • Seedance 2.5 (up to 1,632s of video)
  • Seedance 2.0 (up to 2,352s of video)
  • MiniMax H3 (Up to 2,051s of video)
  • MiniMax H3 Max (Up to 3,333s of video)
  • GPT Image 2 (up to 3,076 images)
  • Nano Banana 2 (up to 2,051 images)
  • Motion graphics (up to 4,000 clips)
  • AI music (up to 3,636 songs)
  • Clone voices and reuse them in projects (up to 8 voices)
  • All AI agent editing capabilities
  • Motion graphics transparent export
  • No export limit

Questions about video to text

Is converting video to text free in ChatCut?

Yes. Transcription, uploads, caption editing and exporting a TXT or SRT file don't use ChatCut credits; you only need a free account. If you ask the ChatCut Agent to do the steps for you, which is what the Transcribe in ChatCut button sets up, Agent messages use credits based on usage. Doing the four steps yourself uses none.

What files can I transcribe?

Video in MP4, MOV, WebM, MKV, AVI or TS, and audio in MP3, WAV, AAC, FLAC or OGG. For the fewest surprises, use H.264 video in MP4, or WAV or MP3 audio. If a file is recognized but fails, check that it plays locally and convert it to one of those.

How do I download the transcript?

Turn on captions and wait until every clip on the active caption track has finished transcribing. Then open Export → Subtitles and choose plain text (.txt) or SubRip (.srt). The file follows the active caption track, so select a translation first if that's the text you want.

Can I edit the transcript before exporting?

Yes. In the Transcript panel, select words and choose Edit text to fix them, or Change speaker to move them to the right person. With captions on, the Content panel also has search and replace. Deleting words in the Transcript panel cuts that part of the video, which is handy for removing mistakes before you export.

Does it label who is speaking?

The Transcript panel shows speaker labels. Double-click a label to rename the speaker, reassign selected words to someone else, or merge two speakers into one.

Which languages can it transcribe?

Speech is transcribed in the language it's spoken in, including English, Chinese, Spanish and Japanese; other languages keep their wording as transcribed. To publish in another language, translate the captions and export the translation as its own file.

What's the difference between a transcript and captions?

A transcript is the full text of what was said, for reading, searching or pasting into notes, so TXT is the usual format. Captions are the same words split into short timed cards shown over the video; export them as an SRT file or burn them into the video when you export it.

Do I need to install anything?

No. ChatCut runs in the browser. There's also a Desktop app for macOS and Windows if you'd rather work with local files.

Keep going: Subtitle generator · Transcript and captions guide · Export subtitles · Supported formats · Get a YouTube transcript · Translate a video

Choose your platform