Audio to text

Turn audio into text, with each speaker separated

Drop in an MP3, a voice note, a video or a link, and Whisperall turns it into editable text in your notes, with each speaker separated and the time of each turn. Files can run up to 10 hours and 5 GB, and you can send up to 500 at once.

Download free

Free to start · No card · Windows, macOS and Linux

A recording in Whisperall with each speaker separated and the time of each turn

How it works

Add your audio
Upload a file, drop a whole batch or paste a link. Audio and video both work.
Pick the language
Leave it on auto-detect or choose one of 9 languages. Speaker separation is on by default.
Get editable text
The transcript lands in your note, with each speaker separated and the start time of every turn.

Formats and sizes

Upload any audio or video file. Whisperall prepares the audio on your computer with a built-in converter, so the usual formats all work.

MP3, WAV, M4A, AAC, OGG, OPUS, FLAC and WMA
MP4, MOV, MKV and WEBM video
Up to 10 hours and 5 GB per file
Batches of up to 500 files, one after another

Speakers and times

Speaker separation is on by default. Each turn gets a label, like Speaker 1 or Speaker 2, and the minute it starts, so you can find a quote fast. Turn it off and you get clean paragraphs without times.

Then put the text to work

The transcript is a regular note. Edit it, search it, link it to a project and ask the assistant about it. Select a passage to focus the assistant on it, or copy the text with each speaker and their times.

A call note with key takeaways and next steps, with the assistant beside it

Straight from a link

Paste a link from YouTube, Google Drive or another site with audio or video. Whisperall downloads the audio on your computer, up to 10 hours and 5 GB. If the video needs a login, it asks before using your browser’s session.

What it doesn’t do

Good to know before you start.

No SRT or VTT subtitle files
No importing a video’s own captions or whole playlists
Timestamps come per speaker turn, not per line
Transcription needs an internet connection

Frequently asked questions

Any audio or video file, such as MP3, WAV, M4A, AAC, OGG, OPUS, FLAC, WMA, MP4, MOV, MKV or WEBM. That includes voice notes saved from WhatsApp.

Up to 10 hours and 5 GB per file. You can upload up to 500 files in one batch, and Whisperall works through them one by one.

English, Spanish, French, Portuguese, German, Italian, Japanese, Korean and Chinese. You can also leave it on auto-detect.

Not as SRT or VTT files. Whisperall gives you editable text in a note, with the start time of each speaker turn.

Yes. The audio of the files and links you transcribe is kept with their note so you can play it back, and you can download it as MP3.

File transcription uses credits from the same pool as everything else. The free plan includes 150 credits to try it, and paid plans start at $9 a month with 2,000 credits.