Voice memo to text in seconds

Voice memos are thinking out loud: the idea captured at a red light, the to-do list dictated between meetings, the lecture snippet you’ll “definitely process later”. The friction was never recording them — it was turning them back into text you can actually use.

Short files are this tool’s natural habitat: a two-minute memo becomes editable text in moments, and there is a Record button right in the page if the thought is happening now. Your files are never uploaded — everything runs on your device.

Checking what this browser supports…

How to transcribe a voice memo

  1. Drop the memo — or record one

    Any recording app’s output works (M4A, MP3, OGG…), or press Record to capture the thought directly in the browser.

  2. Moments later, read it

    Short clips process quickly even on the built-in WebAssembly path; on a machine with a GPU it is faster still.

  3. Copy it where it belongs

    One click copies the plain text into your notes app, task manager, or draft. Exports exist too, if a file is what you need.

Built for quick capture

Record right here

A microphone button in the tool itself — record, stop, transcribe, no separate app, and the recording never leaves the page.

Fast on small files

The model stays loaded between memos, so the second and third clips transcribe with zero startup delay.

Thoughts stay yours

Half-formed ideas deserve privacy most. Memos are processed on your device and are never uploaded anywhere.

Voice memo questions

Can I record directly in the browser?
Yes — the Record button captures from your microphone and transcribes the result on the spot. The browser will ask for mic permission once; the audio itself never leaves your device.
How fast is a typical memo?
That depends on your hardware, so we won’t promise numbers — but short clips generally take a small fraction of their own duration, and the model being cached means no waiting after the first use.
Which recording apps’ files work?
Practically all of them: iPhone Voice Memos (M4A), Android recorders (M4A/OGG/MP3), smartwatches, dictaphones. If it plays in a browser, it transcribes here.
What powers the transcription?
OpenAI’s open-source Whisper model, running locally in your browser via our open-source engine — which is why there is no signup and no upload.
Can I fix words it got wrong?
Yes, click any segment and edit. Dictated speech is fast and mumbly by nature; a ten-second cleanup pass usually beats re-dictating.
How can I check that my voice memo is not being uploaded?
Open your browser's developer tools, switch to the Network tab, and start a transcription with it open. On the first run you will see the Whisper model download once — about 80 MB for the standard model, less or more if you pick a different one — and after that it is served from your browser's cache. What you will not see, on any run, is a request carrying your voice memo. Then sort that list by size: the largest thing the page sends is a few kilobytes of analytics, nowhere near the size of a voice memo. This page loads analytics and advertising like most websites do, which is why the claim is scoped precisely: your files are never uploaded.