How do I get a WhatsApp voice note in here?

In WhatsApp, long-press the voice message → Share/Export, and save the .opus file. Drop it straight into the tool — no conversion needed.

Do iPhone .m4a memos work directly?

Yes. Share the memo from the Voice Memos app (AirDrop, email to yourself, or save to Files), then drop the .m4a here as-is.

My memo is in Portuguese or Spanish — will it work?

Yes. The spoken language is detected automatically and the text comes out in that language; Whisper covers around 100 of them. You can also set the language by hand if you prefer.

Which model should I pick for a voice memo?

Fast is enough for a clear, close-mic memo you only need to skim. Use Accurate or Best when the recording is noisy, the speaker mumbles or the text will be quoted; they need more memory and time.

Will the transcript have punctuation and paragraphs?

Whisper adds punctuation and sentence breaks, so the text reads naturally rather than as one long run. It does not know your intended structure, so headings, lists and paragraph breaks are yours to add afterwards.

Voice Memo to Text — Transcribe iPhone & WhatsApp Memos

Turn iPhone voice memos (M4A) and WhatsApp voice notes (OPUS) into text — privately, in your browser.

Model

Spoken

Output

Timestamps [0:05]

🌍 The spoken language is detected automatically and the transcript comes out in that same language. Set it manually above if your audio is hard to hear, and use Output to translate into English.

⬇️ One-time download: 104 MB (Accurate model 73 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 4-8 min per 10 minutes of audio on a typical laptop.

What exactly is downloaded — and is it safe?

• The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
• They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
• They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
• They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
• Your audio never goes the other way: this site has no server receiving files.

Drop your audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

A voice memo is the fastest way to capture a thought and the slowest way to find it again. Nobody scrolls through forty recordings named by date to find the one with the address or the idea for the pitch. Turning the memo into text makes it searchable, quotable and easy to paste into notes, an email or a to-do list. This page is set up for audio files, and it takes the formats memos actually come in, including the M4A that iPhones produce and the OPUS that WhatsApp uses.

Recognition is at its best on a memo spoken close to the phone by one person, and at its worst on one recorded in a car, across a room or in a café. Choose the Fast model to skim a long memo quickly and the Best model when the words matter, at the cost of more memory and time. The first use downloads the speech model, and a long memo on a phone is noticeably slower than on a laptop. Treat the result as a draft: names, numbers and anything you would act on deserve a listen before you rely on them. In the default Private mode the recording is transcribed in your browser and not uploaded, which is the right standard for a file of someone's voice.

More sizes & options

Frequently asked questions

How do I get a WhatsApp voice note in here?: In WhatsApp, long-press the voice message → Share/Export, and save the .opus file. Drop it straight into the tool — no conversion needed.
Do iPhone .m4a memos work directly?: Yes. Share the memo from the Voice Memos app (AirDrop, email to yourself, or save to Files), then drop the .m4a here as-is.
My memo is in Portuguese or Spanish — will it work?: Yes. The spoken language is detected automatically and the text comes out in that language; Whisper covers around 100 of them. You can also set the language by hand if you prefer.
Which model should I pick for a voice memo?: Fast is enough for a clear, close-mic memo you only need to skim. Use Accurate or Best when the recording is noisy, the speaker mumbles or the text will be quoted; they need more memory and time.
Will the transcript have punctuation and paragraphs?: Whisper adds punctuation and sentence breaks, so the text reads naturally rather than as one long run. It does not know your intended structure, so headings, lists and paragraph breaks are yours to add afterwards.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.