FREE TOOL · ON YOUR DEVICE
Transcribe audio and video to text free
Turn what is said in an audio or video file into text: a voice note, an interview, a lecture or a podcast episode. Transcription runs with Whisper on your device; check the text, copy it or download it as TXT (in paragraphs or with timestamps) or SRT.
- Free, free account required
- TXT and SRT
- Your audio never leaves your device
- Add your audio or video
- Transcribe
- Check and download
HOW TO USE IT
Three steps.
Add your audio or video
MP3, WAV, M4A, OGG, MP4, WebM or MOV with speech, up to 10 minutes. Choose the language: Spanish, English or detect.
Transcribe
Press “Transcribe to text”. The first time the model downloads; after that it takes about as long as the audio on a recent computer.
Check and download
Fix the text, copy it or download the TXT in paragraphs or with timestamps, and the SRT by sentence.
NEXT STEP
Keep going with these tools
Transcribe to text: common questions
How accurate is the transcription?
With clear speech and little noise it usually gets most words right. It can get names, background music, strong accents or overlapping voices wrong, and it does not tell speakers apart. Check the text before using it.
Does it work with WhatsApp voice notes?
Yes, if your browser can play the file (voice notes are usually OGG or OPUS, which Chrome, Edge and Firefox read). Save it to your device and add it here.
What if my audio is longer than 10 minutes?
Cut it into parts of up to 10 minutes and transcribe them one by one. An audio file up to 15 minutes can be cut right here with our MP3 cutter; cut a video or a longer audio file in your phone’s gallery or in your editor (Trim video also stops at 10 minutes). The limit keeps it working well on phones too.
What does the transcription?
Whisper (OpenAI’s speech recognition model, MIT-licensed weights) run by transformers.js (Apache 2.0 licence) inside your browser, the same one our Auto subtitles tool uses. The first time the model downloads (about 77 MB in “Normal” and about 250 MB in “High”) and your browser keeps it.
Is my audio uploaded to a server?
No. The audio is read and transcribed inside your browser and is not sent to Cocuyo or to any third party. Only the speech model downloads, once, from our servers.
Is it really free?
Yes. You can try it before signing up; to keep using it, we ask for a free account, with no subscription. It uses no credits and does not count toward your 30 welcome uses: it has no usage cap.
What are the limits?
One audio or video file up to 300 MB and 10 minutes that your browser can play. Transcription runs on the device: on a phone it can take much longer than on a computer.
Learn how to…
MORE FREE TOOLS
Other audio tools
All free tools
WHEN YOU WANT TO CREATE
Create voices and narration with AI.
Cocuyo’s Studio brings 30+ AI models for image, video and voice together. You see the credit cost before generating, and credits never expire.