Turn any audio into text
Drop an MP3, WAV, M4A or voice recording and the engine writes down the speech with timestamps, and can translate it — right on your device. Nothing is uploaded.
Drop a video or audio file
MP4, MOV, WebM, MP3… · stays on your device
Private by design
The audio is extracted with ffmpeg.wasm and transcribed by a Whisper model that runs inside your browser. Your video never leaves your device.
How video-to-text works
Add a video
Drop any video or audio file. It stays on your device — nothing is uploaded to a server.
Transcribe
The browser extracts the audio and a Whisper model writes down the speech with timestamps for subtitles.
Translate & export
Optionally translate the text into another language, then download it as SRT, VTT or plain text.
Made for creators, editors and teams
Accurate speech-to-text
A Whisper model transcribes dozens of languages with timestamps, right in your browser.
Subtitles that fit your brand
Style burned-in captions — font, size, colour, position and a karaoke word highlight.
Translate into six languages
Reach new audiences: translate the transcript and export translated subtitles.
Private, free, no watermark
Nothing is uploaded, there is no account, no limit and no watermark on the output.
What people use video-to-text for
From captioned Reels to full transcripts — one video in, text and subtitles out.
Subtitles for Reels & TikTok
Add burned-in captions so your videos work with the sound off and keep viewers watching.
YouTube captions & transcripts
Export SRT/VTT to upload, or a clean transcript for the description and chapters.
Repurpose video into articles
Turn talks, webinars and interviews into editable text you can publish as a post.
Translate videos for new markets
Localise subtitles into other languages to reach a wider, international audience.
Accessibility & compliance
Provide captions so your content is accessible and meets accessibility requirements.
Notes from meetings & lectures
Drop a recording and get searchable, editable text you can skim and share.