Video to Text: Transcribe Any Video
AITurn video to text without uploading the video. Drop an MP4, MOV, MKV or WebM file and Whisper, running in your browser, transcribes its soundtrack into an editable transcript with timestamps. The video plays beside the text, so a click on any line jumps to that moment. Save it as TXT, Word, SRT or VTT. There is no length cap, sign-up or watermark.
- Runs on your device
- Whisper AI
- WebCodecs · GPU
- Works offline
Updated
How to transcribe a video to text
Step 1: Drop one or more video files on the box above: phone clips, Zoom or Teams recordings, screen recordings or lectures.
Step 2: Set the Spoken language (or keep Detect automatically) and pick a Speech model. Balanced suits most videos.
Step 3: Press Transcribe and confirm the one-time model download. Only the soundtrack is read; the picture is skipped.
Step 4: Correct the text while the video plays alongside, then Copy it or export TXT, DOCX, SRT, VTT or JSON.
Good to know
Settings explained
- Spoken language
- Picking the language skips detection and improves accuracy on short clips.
- Speech model
- Downloaded once after you confirm, then cached for offline use. Bigger models are more accurate but slower.
- Fastest: from 44 MB · good for clear speech
- Balanced: from 80 MB · recommended
- Accurate: from 252 MB · slower
- Best: from 566 MB · needs WebGPU
Formats
Batch-friendly: add many files and they are processed one after another — if one fails, the rest still finish.
How it runs
- Whisper speech model
- Speech recognition uses an open Whisper model. It downloads once after you confirm its size, then runs on your device — on the GPU via WebGPU when available.
- Hardware video engine
- Video is decoded and encoded by your device’s media hardware through WebCodecs — usually several times faster than real time.
Transcript, subtitles or captions: which do you need?
A transcript is text to read, search and quote. Subtitles are the same words cut into timed cues for a player. Burned-in captions are drawn into the picture so they show on every platform. This page makes the first two; the subtitle generator styles and burns captions, and add subtitles to video attaches an SRT you already have.
| You want | Use | You get |
|---|---|---|
| Meeting notes, quotes, a blog post | This page, TXT or DOCX | Paragraphs, with or without [0:00] stamps |
| Captions to upload to YouTube or an editor | This page, SRT or VTT | A subtitle file timed to the speech |
| Captions visible in a Reel or TikTok | Subtitle generator | Styled captions burned into the video |
| Permanent subtitles from an existing SRT | Burn subtitles | The SRT drawn into the picture |
| The transcript in English | This page, Translate to English | English text from any spoken language |
What is video transcription?
Video transcription is writing down everything said in a video, with times, so you can search it, quote it or turn it into subtitles. Here it is done by Whisper, OpenAI’s open speech-recognition model, inside your browser tab.
Only the sound matters, so ProMedia reads just the video’s audio track and skips the picture. The audio is decoded in a stream and resampled to 16 kHz mono as it arrives, which keeps long recordings from filling your memory. If a file holds several audio tracks, the main one is transcribed.
Transcribe a Zoom, Teams or Google Meet recording
Meeting recordings are ordinary video files once they are on your computer, so the only work is finding them.
Zoom
Local recordings are saved in the Zoom folder inside Documents, as an MP4 plus an audio-only M4A. Either file works; the M4A is smaller. Cloud recordings can be downloaded from the Zoom web portal first.
Microsoft Teams
Recordings are stored in OneDrive or SharePoint. Open the recording, download the MP4, then drop it here. Nothing goes back to Microsoft.
Google Meet
Recordings land in the organiser’s Google Drive, in the Meet Recordings folder. Download the MP4 to your device before transcribing.
Screen recordings
Windows Game Bar saves MP4 files to Videos › Captures, iPhone screen recordings are MP4 too, and the Mac screenshot tool records MOV files. All of them open here directly.
Which video formats can you convert to text?
Any common video format works, because only its sound is decoded. MP4 to text is the most common job, and most MP4 files have AAC audio that every browser reads without extra downloads.
| Format | Typical source | How the sound is decoded |
|---|---|---|
| MP4, MOV, M4V | Phones, cameras, Zoom, screen recordings | Directly by the browser |
| MKV, WebM | OBS, downloads, browser recordings | Directly for AAC, Opus, Vorbis and MP3 audio |
| TS, MTS, M2TS | Camcorders, TV and stream captures | Directly, or with FFmpeg for AC-3 audio |
| AVI, WMV, FLV, MPEG, VOB | Older cameras, DVDs, archives | FFmpeg decoder, which loads once |
How long can the video be?
There is no time limit, only your device’s memory. Whisper needs the speech as 16 kHz samples of 4 bytes each, so every minute of video becomes a fixed amount of working memory, no matter how large the video file is. A 4K recording costs the same as a 480p one. Hours of video are fine on a laptop or desktop; on a phone, shorter videos are safer.
| Video length | Decoded speech in memory |
|---|---|
| 10 minutes | about 38 MB |
| 1 hour | about 230 MB |
| 2 hours | about 461 MB |
| 3 hours | about 691 MB |
Why convert video to text with ProMedia
- The video never leaves your device. Meetings, interviews and classes stay private; there is no server to upload to.
- Watch while you correct. The picture plays next to the transcript, and a click on a timestamp jumps to that line.
- Several videos in one go. Each file gets its own transcript tab, ready to export.
- Free, with no minute allowance. No account, no queue, no watermark on the text or subtitles.
- Offline after the first run. The speech model is cached in your browser.
Transcribe a video on iPhone, Android, Mac or Windows
The steps are the same in every modern browser. What changes is where your videos are stored.
iPhone and iPad
In Safari, tap the drop zone and choose Photo Library for camera clips and screen recordings, or Choose Files for downloads. Phones use the Fastest model by default; long lectures go quicker on a computer.
Android
In Chrome, tap the drop zone and pick the video from your gallery or Downloads. The transcript appears on the phone; nothing is sent anywhere.
Mac
Drag the MOV or MP4 from Finder. Chrome and Edge use WebGPU on Macs, which makes transcription faster and unlocks the Best model.
Windows 10 and 11
Drag the file from File Explorer into Chrome, Edge or Firefox. Transcripts and subtitle files save to your Downloads folder.
Tips & troubleshooting
Only need the sound later? Save it separately with extract audio from video; audio-only files are also easier to keep.
For recordings without a picture, audio to text covers MP3, M4A and voice-memo workflows.
Publishing on YouTube? Export SRT for the captions and run the same video through the YouTube chapters generator for “00:00” timestamps.
A noisy meeting room? Clean the soundtrack first with remove background noise, then transcribe the cleaned video.
Short clips under about ten seconds: choose the Spoken language yourself, because automatic detection has little to go on.
Video to Text FAQ
How do I transcribe a video to text for free?
Drop the video on this page, pick the language and a speech model, and press Transcribe. The model downloads once after you confirm and runs on your device, so there is no fee, minute limit or watermark. Export the result as TXT, DOCX, SRT, VTT or JSON.
How do I convert MP4 to text?
Drop the MP4 here and press Transcribe. Its AAC soundtrack is read directly by the browser, so nothing else needs installing. Copy the transcript, download it as a text file or Word document, or choose SRT if you want subtitles instead.
Can I transcribe a YouTube video?
Only if you have the video file, for example your own upload or a lecture you were given. ProMedia does not download from YouTube or any other site. Drop the file here and the transcript is made on your device.
Can I transcribe a video on iPhone?
Yes. Open this page in Safari, tap the drop zone and pick the clip from Photo Library or Files. The phone does the work, so very long videos are slower than on a computer, and the Fastest model is chosen to save memory.
Can I get subtitles instead of a transcript?
Yes. Export SRT or VTT from the transcript editor; the cues keep the original timing. For captions styled and burned into the picture, use the subtitle generator, which times each caption word by word.
Can it transcribe a video in another language into English?
Yes. Switch on Translate to English before transcribing and the transcript is written in English, whatever language is spoken. It works with the Fastest, Balanced and Accurate models; the Best model only transcribes.
Is the video uploaded anywhere?
No. The video is read by your own browser. The speech model downloads once from the Hugging Face CDN after you agree, and older formats such as AVI or WMV also load an FFmpeg decoder from this site. You can switch to airplane mode after the first run and transcribe offline.