Upload a video or an audio file and get back a readable transcript with timestamps. When more than one person talks, each paragraph is marked Speaker 1, Speaker 2 and so on. TXT, SRT and VTT files are included.
Need something else? More Captions & Text tools or all 29 tools
Video to Text is a tool that turns the speech in a video or audio file into a written transcript. You upload an MP4, MOV, WEBM, MP3, WAV or M4A file up to 10 minutes. The AI writes out every word, splits the text into paragraphs with a timestamp at the start of each, and labels who is speaking when there is more than one voice. You can read it on the result screen or download it as TXT, SRT or VTT.
Sign in and upload the file you want to transcribe: MP4, MOV or WEBM up to 200 MB, or MP3, WAV or M4A, up to 10 minutes long. It needs to have speech in it.
Pick the language people speak in the recording, or leave it on Detect automatically. Choosing it yourself helps with short clips and strong accents.
Press Transcribe. The transcript shows up on the result screen with TXT, SRT and VTT downloads, and it's saved in My Videos.
The transcript isn't one long block. A new paragraph starts when the speaker changes, after a pause longer than a second and a half, or at the end of a sentence once a paragraph runs long. Each one opens with a timestamp like [2:15], so you can jump to that moment in the recording.
When two or more people talk, each paragraph starts with Speaker 1, Speaker 2 and so on, numbered in the order they first speak. A solo recording gets no labels, just clean paragraphs.
Along with the plain-text transcript, you get SRT and VTT files cut into short lines of two to four words, timed to the speech. Upload them to a video platform as closed captions, or import them into your editor.
Upload a video and the sound is taken out of it first, or upload audio directly. Pick the spoken language from English, Turkish, Spanish, Portuguese, French, German, Italian, Arabic, Hindi, Japanese, Korean, Indonesian or Russian, or let the AI detect it.
Transcription costs 10 credits per started minute of the file. A 4-minute voice memo is 40 credits, and a full 10-minute interview is 100. The price is shown before you start.
Transcribing by hand means pausing, rewinding and typing for longer than the recording lasts. Here the AI writes it out and marks who spoke when.
| Feature | Video to Text | Typing a transcript by hand |
|---|---|---|
| Writing it out | Every spoken word, transcribed by the AI | Type while pausing and replaying the recording |
| Speakers | Speaker 1, Speaker 2 and so on, added when two or more people talk | Work out and label each voice yourself |
| Timestamps | A time at the start of every paragraph | Note the times down by hand |
| Subtitle files | SRT and VTT in short timed lines, in the same job | Time every caption line on a timeline |
| Languages | 13 spoken languages, or auto-detect | Someone who speaks the language |
| Price | 10 credits per started minute, up to 10 minutes per file | Hours of your time, or a per-minute transcription service |
You recorded a 9-minute conversation with a guest and need quotes, chapter times and a written version for your website.
Your talking-head video is ready, and you want viewers to be able to switch captions on without adding them to the picture.
A 10-minute section of a class or a team call contains the details you need, and scrubbing through the recording is slow.
Turn an episode or a street interview into a speaker-labelled transcript for show notes, quotes and blog posts.
Get SRT and VTT caption files for uploads, and a written script you can turn into a description or a post.
Transcribe a lecture clip, a recorded interview or a field recording so you can quote and search it.
Write up a recorded meeting, a webinar section or a customer video for your brand's notes, help pages or social posts.
10 credits per started minute of the file. A 2-minute clip costs 20 credits and a 10-minute recording costs 100. The price is shown before you start.
Upload the video, pick the spoken language or leave it on auto-detect, and press Transcribe. The transcript appears on the result screen with TXT, SRT and VTT downloads.
Yes. When more than one person talks, each paragraph is labelled Speaker 1, Speaker 2 and so on. A single speaker gets no labels.
Yes. Every paragraph starts with the time it begins in the recording, such as [1:42]. The SRT and VTT files are timed line by line.
Yes. Upload MP3, WAV or M4A as well as MP4, MOV or WEBM video. The limit is 10 minutes per file.
English, Turkish, Spanish, Portuguese, French, German, Italian, Arabic, Hindi, Japanese, Korean, Indonesian and Russian. You can also let the AI detect the language.
Up to 10 minutes, with videos up to 200 MB. For longer recordings, split them into parts and transcribe each one.
Yes. Every transcription comes with an SRT and a VTT subtitle file, cut into short timed lines, ready to upload as closed captions.
Yes. Sign in with Google or email; each job costs credits from your balance, and the result is saved in My Videos.
If a job can't finish, the credits it used go back to your balance automatically.
Transcribe any video or audio to text with speaker labels, plus SRT and VTT. 10 credits / min, and the result is saved in My Videos.
