Video to Text

Transcribe video and audio to text, SRT, or VTT in your browser with Whisper. No upload, no signup, no watermark.

Drop a video or audio file here

or click to select a file

MP4, WebM, MOV, MP3, WAV, M4A…

Runs 100% in your browser — the FFmpeg engine (~25 MB) and the Whisper model download on first use and are cached afterwards. Your file never leaves your device.

What is Video to Text?

Video to Text is a free, browser-based transcription tool that turns spoken audio in a video (or an audio file) into written text. It extracts the audio with FFmpeg and runs OpenAI's Whisper speech-recognition model entirely on your device — so nothing is uploaded — and exports the transcript as plain text, SRT, or VTT subtitles.

How to use

  1. Drop a video or audio file (MP4, WebM, MOV, MP3, WAV, and more).
  2. Choose a language (or leave Auto-detect) and a model — Fast, Balanced, Accurate, or Max (best accuracy, WebGPU).
  3. Click Transcribe, then copy or download the text as TXT, SRT, or VTT.

Frequently asked questions

How do I convert a video to text for free?

Drop your video or audio file, pick a language and model, then click Transcribe. The tool extracts the audio and runs OpenAI Whisper directly in your browser, then gives you the transcript as plain text, SRT, or VTT. Nothing is uploaded and there is no signup.

Is my video uploaded to a server?

No. Everything runs locally in your browser using FFmpeg (WebAssembly) for audio extraction and a Whisper model compiled to run on your device. Your file never leaves your computer, which makes it safe for private or confidential recordings.

What languages are supported?

Whisper is multilingual and supports dozens of languages including English, Spanish, Portuguese, French, German, Japanese, and Chinese. Leave the language on Auto-detect and it will figure it out, or pick a specific language to improve accuracy.

Why does the first transcription take a while?

On first use the browser downloads the FFmpeg engine (~25 MB) and the Whisper model (from 40 MB up to ~1.6 GB for the optional Max model, depending on the quality you choose). Both are cached afterwards. Transcription speed also depends on your device — machines with WebGPU support are much faster than CPU-only.

Last updated

Powered by maratool