Frequently asked questions
Everything you need to know about turning audio and video into text with Herramientas Libres.
Is it really free? What's the catch?
It's free and there is no paid plan. Transcription runs on your device, so we don't pay for servers per minute. The site is supported by ads.
Are there limits on minutes, files or size?
We don't set any limits. The only practical limit is your device's memory, because the whole audio is loaded into the browser. A modern computer handles long recordings fine; on phones we recommend recordings under an hour and the “Fast” quality. If a very long file fails, split it into parts.
Do I need to sign up or install anything?
No. You only need an up-to-date browser (Chrome, Edge, Firefox or Safari) on a computer or phone.
Is my audio uploaded to a server?
No. The file is opened and processed inside your browser. The only things downloaded from the internet are the public speech recognition model and the page's code. Your audio and your transcript are never sent anywhere.
Which formats are supported?
MP3, WAV, M4A, AAC, OGG, OPUS, FLAC and WEBM audio, and MP4, MOV, WEBM and usually MKV video. Your browser's decoder is used, so a rare format might not open; try another browser or convert the file to MP3.
How accurate is it?
We use Whisper, a well-known open-source speech recognition model. With clear audio the result is usually very good, with punctuation. Noise, overlapping speakers or very technical vocabulary cause more mistakes, which is why you can edit the text before downloading. The “Most accurate” quality helps with difficult audio.
How long does it take?
It depends on your device, the chosen quality and whether your browser can use the graphics card (WebGPU). On a computer with WebGPU it's usually much faster than the audio length. Without WebGPU, or on phones, it may take as long as the audio or longer. You'll see progress and an estimated time left while text appears.
Which languages are supported?
English, Spanish, Portuguese, French, Italian, German, Catalan and many more. Choose the language or let it be detected automatically. You can also translate any audio into English.
Does it tell speakers apart?
Not yet. You get continuous text with timestamps, but speakers are not labelled.
How do I make subtitles for a video?
Upload the video, transcribe it and click “Download SRT” (or VTT). Most video editors, players and video platforms accept that file.
I get an error. What should I do?
Update your browser, choose the “Fast” quality, close other tabs to free memory, split very long files, or convert unreadable files to MP3. If it still fails, contact us with your browser and file type.