Voice Memo to Text
Get your spoken notes, ideas and reminders as text you can paste anywhere.
On iPhone, open Voice Memos, tap the recording, then Share and Save to Files. On Android, recordings are usually in the Recordings folder. Then choose the file here.
The transcription runs inside your browser with Whisper, the open speech recognition model by OpenAI. Your audio is never uploaded: only the model itself is downloaded once, then your browser keeps it, so the next files start right away.
Speech model: Whisper by OpenAI (MIT). Runs with Transformers.js (Apache-2.0).
How it works
- Drop your file Audio or video: MP3, M4A, WAV, MP4, MOV, WebM, OGG and more.
- Pick the language The language that is spoken. Choose More accurate for noisy recordings or strong accents.
- Transcribe and save Copy the text, or save it as TXT, SRT or VTT subtitles.
FAQ
Is my recording uploaded?
No. It is transcribed on your device. Only the speech model is downloaded, never your audio.
Is there a length limit?
We don't set one. Long files take longer: on a recent computer with Chrome or Edge, an hour of audio takes about 10 minutes. Phones and older computers are slower.
Which languages work?
Whisper understands around 100 languages, including English, Spanish, German, French, Portuguese, Hindi, Arabic, Japanese and Indonesian. Accuracy is best for widely spoken languages.
Is it free?
Yes. No account, no minutes limit, no watermark.