Start a project →

Free Video Transcription: video to text and SRT subtitles in your browser

Choose a video or audio file and get the transcript as plain text, plus SRT and VTT subtitle files with timings, ready for YouTube. It uses Whisper, an open speech recognition model, running inside your browser: your file never leaves your device, and there is no signup.

Updated · Built by Kevin Tabares, long-form YouTube editor at Umbrella Creators.

Transcribe a video or audio file

Your file stays on your device. Nothing is uploaded: your browser decodes the audio and the speech model turns it into text right here, in this tab. Only the model is downloaded, once, from Hugging Face.

How to use it

  1. Choose your video or just its audio (MP4, MOV, WEBM, MP3, WAV or M4A). It can be the finished edit or the raw recording.
  2. Pick the model: Fast (about 64 MB to download) or Better (about 136 MB, more accurate and slower). Leave the language on Detect automatically or choose it yourself, then press Transcribe.
  3. The first time, your browser downloads the model from Hugging Face and keeps it, so next time it starts in seconds. Then the audio is processed in 30 second windows that overlap a little, and you can see the progress.
  4. Read the transcript, then download the SRT (or VTT) and upload it to YouTube, or copy the text for a description, a blog post or a script.

A computer is the best place for this: a long file can take a while on a phone and use a lot of battery, and the limit is 60 minutes per file. On browsers with WebGPU (recent Chrome and Edge) the model runs on the graphics card and is much faster; elsewhere it runs on the processor. Subtitles are split into cues of up to 2 lines of 42 characters, the usual reading limit.

FAQ

Is this video transcription tool free?
Yes. There is no signup, no watermark and no limit on how many files you transcribe. The only cost is your own computer doing the work, because the speech recognition runs inside your browser.
Does it upload my video?
No. Your browser reads the file and turns it into text on your own device; the video or audio never leaves this tab. The only thing that is downloaded is the speech model (Whisper), once, from Hugging Face. Your browser keeps it, so the next time it starts much faster.
Which languages does it transcribe?
Whisper understands around 99 languages. The menu lists English, Spanish, Portuguese, French, German and Italian, and "Detect automatically" can pick any of the others. Results are best in widely spoken languages like English and Spanish, and weaker in languages with less training data.
How accurate is the transcript?
It depends mostly on the audio: one clear voice close to the mic gives a very usable draft, while music under the voice, several people talking at once or a noisy room make it worse. The "Better" model makes fewer mistakes than "Fast". Always read the result before you publish it, especially names, brands and numbers, which speech models often get wrong.
How do I add the SRT file to my YouTube video?
In YouTube Studio, choose Subtitles in the left menu and pick your video. Click Add language and choose the language, then under Subtitles click Add, choose Upload file, select With timing, click Continue, pick the .srt file and Save. These are the steps in YouTube Help (read October 20, 2026).

Who made this

I'm Kevin Tabares. I've edited long-form YouTube videos since 2015 (1,277 videos and 152.2M+ views tracked on YT Jobs) for channels like Rex & Alexa, Puff and Mud. I built this so you can get a first draft of your transcript and subtitles in minutes, without uploading your video anywhere. If you want an editor for your channel, get in touch.

More free tools

A subtitle checker for your SRT and VTT files, a silence detector that finds the dead air, a LUFS meter for your video's loudness and an audio channel checker, all free and without signup.

See all tools →