Upload a video and get what is said in it as text with timestamps. Video transcription on Kotosay works with MP4, MOV, WEBM, MKV and AVI, and your browser normally sends only the sound, so even a large file uploads as a small one.
00:00:05Wet your hands first, the clay should never feel dry.
00:00:11Centre it before you open it, otherwise the wall goes thin on one side.
00:00:18Slow the wheel down as the walls go up.
00:00:24We fire the pieces on Thursday.
Pick the file on your computer or phone. Your browser takes out the audio track and compresses it.
The spoken language is detected for you. Correct any word in the editor and the timestamps stay.
Copy the text, or with Unlimited download TXT, DOCX, PDF, or SRT and VTT subtitles.
A product demo or walkthrough as written steps for a help page.
A recorded call saved as MP4, transcribed after the meeting, with a timestamp on every line.
A lesson as searchable text, plus SRT subtitles for the course platform.
Clips filmed on an iPhone or Android phone, uploaded straight from the phone browser.
A long session as text to quote from, up to 10 hours per file with Unlimited.
Captions for Reels, Shorts and TikTok from the clip you filmed yourself.
| No account | Free account | Unlimited | |
|---|---|---|---|
| Price | Free | Free | $9.99 a month, or $119 paid once a year |
| Files | Your first file | 3 a day | 3 at once |
| Transcribed per file | First 5 minutes | First 5 minutes | Up to 10 hours |
| Read, edit and copy | Yes | Yes | Yes |
| TXT, DOCX, PDF, SRT and VTT | No | No | Yes |
| Translation | No | No | Yes |
Unlimited works on up to 3 devices and cancels in one click. Your renewal date is in your account at any time. Single file opens one whole video for $4.99, paid once.
Normally only the sound of your video is uploaded. We delete the audio automatically 24 hours after transcribing it. The transcript stays until you remove the file or the whole account.
A transcript comes from what people say, so the picture plays no part. When you pick a video, your browser extracts the audio track and compresses it before anything is sent.
A large screen recording and a small MP3 of the same talk hold the same words. Usually only the sound is uploaded, so a slow connection matters much less. If your browser cannot extract it, the original file is sent instead.
TipWant an MP3 of the video to listen to later? The MP4 to MP3 converter makes one in your browser, free.
MP4, MOV, WEBM, MKV and AVI upload directly. Here is where each one usually comes from.
Music added in the edit often costs words in the transcript. If you cut the video yourself, export a version with the music track muted and upload that one. The words and their timing stay the same, and the text comes out cleaner.
Phone videos filmed outdoors pick up wind, and a camera across the room hears the walls more than the voice. A cheap clip-on microphone near the person talking helps more than a better camera. For a recording you already have, check the unclear passages in the editor against your own copy of the video.
Yes. The transcript of a video is already timed, so it can become subtitles. With Unlimited, download SRT or VTT and add the file in YouTube Studio, Vimeo or your video editor. The subtitle generator page covers SRT, VTT and readable line length.
To transcribe a video, Kotosay needs the file itself. For a clip of yours on TikTok, Instagram or YouTube, take the original from your camera roll or export it from the app, then drop it in here.
For a YouTube video, paste its link on the YouTube transcript page and Kotosay transcribes the audio.
People look for an MP4 to text tool, a video to text converter or a way to convert video to text. On Kotosay all three mean the same upload. Pick the file, and the spoken words come back as text in the editor.
You can transcribe video in any of the formats above, from a short phone clip to a recorded class. When the text is ready, fix names in the editor and copy it, or export it with Unlimited as a document or as subtitles.
In a recorded interview or a panel, the transcript runs as one text without names. Where the voice changes, note the time on that line, play your copy from there and type the name at the start of the line in the editor.
UX researchers and support teams often record screen sessions where someone thinks aloud while clicking through a product. Note the timestamp of each task as you read, and you can cut the matching clips from the video later.
A free account transcribes the first 5 minutes of each video, 3 files a day, and shows a note where the locked part starts. Unlimited takes videos up to 10 hours, so a full webinar or lecture fits in one file.
Every transcript opens in the editor, free on every plan, where the timestamps stay in place while you fix words. Unlimited adds TXT, DOCX and PDF for documents, SRT and VTT for subtitles, and translation into another language with the timing kept.
Upload the video at the top of this page. Your browser extracts the sound, Kotosay transcribes it and opens the text in the editor with timestamps. Your first file shows 5 minutes without an account, and a free account transcribes the first 5 minutes of each video, 3 a day.
MP4, MOV and WEBM all upload directly, and so do MKV and AVI. That covers iPhone and Android videos, Zoom and Teams recordings, browser recorders and most editing exports. Upload the file as it is, because your browser takes out and compresses the audio for you.
You can pick a video of up to 1 GB. Your browser normally takes out the sound and compresses it, so the upload is much smaller than the video. A free account transcribes the first 5 minutes of each file, and Unlimited takes videos up to 10 hours, 3 of them at once.
Yes, with Unlimited. Download the transcript as SRT or VTT and you have a subtitle file timed to the speech. Both formats work in YouTube Studio, Vimeo and editors such as Premiere Pro and DaVinci Resolve. Fix any word in the editor first, and the timing stays.
Upload the recording file like any other video. Screen recorders usually save MP4, MOV or WEBM, which all work. For the full text of a webinar, Single file or Unlimited takes files up to 10 hours. Every line carries a timestamp, so you can find a slide or a question in your recording.
Yes. Transcription works in 90+ languages, and the spoken language is detected for you. You can also pick it from the list. To get the text in a second language, upload the video on the translate page with Unlimited, and every translated line keeps its timestamp.
With Unlimited, export it as TXT, DOCX or PDF. TXT opens anywhere, DOCX opens in Word and Google Docs, and PDF is ready to share. On the free plan, copy the text from the editor and paste it into any document or notes app you use.
Upload the video file instead. Take the original clip from your camera roll, or save it from your own account in the app, then drop it in here. For a YouTube video, paste its link on the YouTube transcript page and Kotosay transcribes the audio.
Yes. Both save MP4 files, which upload directly. Download the recording from Zoom, or from OneDrive or SharePoint for Teams, then drop it in here. Fix names in the editor, and with Unlimited export DOCX or PDF to share the meeting text with your team.
Upload the video as it is. Your browser already takes out and compresses the sound before the upload. The MP4 to MP3 converter is there for when you want an MP3 for yourself, for example to listen to a talk on the go.
Yes. Your first video needs no account and shows its first 5 minutes in full. A free account then transcribes the first 5 minutes of 3 videos a day, and you can read, edit and copy every transcript. A longer video is still accepted, and the rest stays locked.
Normally only the sound of the video is uploaded. We delete the audio automatically 24 hours after transcribing it, and the transcript stays until you delete it. You can remove a single file, the whole account, or ask us to delete your data. If your browser cannot take the sound out, the original file is sent instead and deleted the same way.
