Audio to text, free and private

Choose a recording and Whisper AI types it out on your own device, line by line with timestamps. Copy the text or download it as TXT, SRT or VTT.

How to convert audio to text

1. Choose an audio file: MP3, M4A, WAV, OGG, OPUS, AAC or FLAC, or drop it on the box.
2. Pick a mode. Balanced suits most English recordings; Accurate is better for Indian languages, accents and noisy rooms.
3. Choose the spoken language, or leave it on Detect automatically.
4. Watch the lines appear, then copy the text or download it as TXT, SRT or VTT.

Getting a cleaner transcript

Speech models are only as good as the sound they hear. Record close to the speaker, away from fans and traffic, and avoid two people talking at once. A phone placed on the table in front of a speaker usually beats a laptop microphone at the back of a room.

Always check names, numbers and technical words before you use the text. The model writes what it thinks it heard, so a misheard figure looks just as confident as a correct one.

Free, private and without limits

Most online transcription services upload your recording to their servers and limit free users to a few files or minutes a day. Here the Whisper model runs in your own browser, so there is no account, no daily limit and no upload, and the tool keeps working offline once the model is cached.

Frequently asked questions

Is my recording uploaded to a server?

No. The speech model is downloaded to your browser once and the audio is transcribed on your own phone or computer. The file never leaves your device.

Why is the first transcription slower?

The first time, your browser downloads the speech model (about 40 MB for Quick, 80 MB for Balanced, 250 MB for Accurate). After that it is cached and starts in seconds, even offline.

How long can the recording be?

There is no fixed limit. An hour-long lecture works on most laptops; on a phone, recordings under about 30 minutes are more comfortable. Lines appear while it works, so you can stop at any point and keep what is done.

Which languages does it understand?

Whisper recognises around 100 languages, including English, Hindi, Bengali, Marathi, Tamil, Telugu, Gujarati, Kannada, Malayalam, Punjabi and Urdu. Pick the language for better accuracy, or leave it on automatic.

Which file types work?

Anything your browser can play: MP3, M4A, WAV, OGG, OPUS, AAC, FLAC and the sound from MP4, MOV and WEBM videos.