Which audio file types can I upload?

MP3, M4A, WAV, AAC, OGG, Opus, FLAC, WebM, MP4 and MOV. Video files are transcribed from their audio track.

How big a file can I upload for free?

The free plan takes files up to 10 MB, which is about 10 minutes of a typical MP3, and includes 30 minutes of transcription a month. Paid plans, starting with the Creator plan, take files up to 1 GB. If the file is already online, pasting its link avoids the upload limit.

Do I need an account to transcribe an audio file?

Yes, a free one. The transcript is saved to your library so you can edit it and export it again later. A podcast link pasted on the homepage can be previewed without an account; an uploaded file cannot.

Will it tell the speakers apart in my recording?

Yes, on every plan. Each voice is labelled Speaker 1, Speaker 2 and so on, and you can rename them in the editor. The names carry through to every export.

How accurate is audio to text transcription?

Close to word for word on a clear recording. Background noise, people talking over each other and unusual names lower it, so check names before you quote them.

Can I turn a recording into subtitles?

Yes. Export the transcript as SRT or VTT and the timings come with it, ready for a video editor or an HTML5 player.

Is my uploaded audio kept?

The audio is kept only while it is being transcribed, then deleted. The transcript stays in your library until you delete it.

MP3 to text,
with who said what.

Upload an MP3, WAV, M4A or any common audio file and get the transcript back with each speaker labelled and every line timed. Edit it, then export it in seven formats. Free files up to 10 MB.

Sources in

How it works

From audio file to transcript

Nothing to install. Upload from your browser and the transcript opens in the editor.

Choose your audio file
Drop in an MP3 or any common audio or video file: MP3, M4A, WAV, AAC, OGG, Opus, FLAC, WebM, MP4 and MOV. If the file is already online, paste its link instead.
Sign in and transcribe
A free account keeps the transcript in your library. The language is detected for you, and speakers are separated automatically.
Edit, then export
Fix a name once and it changes everywhere, then download it as TXT, MD, SRT, VTT, JSON, DOCX or PDF.

What you get

More than the words

Audio or video files

MP3, M4A, WAV, AAC, OGG, Opus, FLAC, WebM, MP4 and MOV. A video file is transcribed from its sound track.

Speakers kept apart

Each voice is labelled, so an interview reads as a conversation rather than one block of text.

Timestamps on every line

Click a line to hear it, and keep the timings for subtitles or quoting.

An editor, not a text dump

Correct words and rename speakers before you export, and the exports pick up your edits.

Most languages

The language is detected from the audio, or you can set it yourself before transcribing.

Seven export formats

TXT, MD, SRT, VTT, JSON, DOCX and PDF, all on every plan.

Exports

Download it in the format you need

.txt

Plain text

Notes, articles and quoting.

.md

Markdown

Title, speakers and paragraphs intact, for Obsidian, Notion or any notes app.

.srt

SubRip subtitles

Cue-timed subtitles for video editors.

.vtt

WebVTT

Captions for HTML5 video and embeds.

.json

Structured JSON

Timestamps and speaker labels as data.

.docx

Word document

Speaker headings and timestamps as real formatting.

.pdf

Print-ready PDF

Paginated and page-numbered, for sharing or marking up.

While you are here

Discover PodcastsToText

The transcript is where it starts. Here is what the rest of the studio does with it.

Your episode opens in an editor.

Click a word and you hear it. Change a speaker name once and it changes everywhere. The whole episode is one page you can actually read, with the line playing highlighted as it goes.

Try the live demo

EditCopyExportShareContent

Transcribed from the episode link · click any line to seek

Marios

Have you ever listened to a podcast and wish you could read what was being said?

Maybe to quote it, study it, or just to find that one line again without re-listening to the whole podcast.

Hey everyone, I'm Marios and I'm really excited to introduce you to my new project,

podcasttotext.com.

It's a web-based app that converts podcast episodes from Spotify and Apple Podcasts into clean, accurate text in just seconds.

Why did I build this up? You may ask.

I built it because I listened to a lot of podcasts.

And at the end of each episode, I was forgetting what was being said.

So I wanted a way to quickly take notes or revisit specific moments without rewinding,

without re-listening the whole podcast.

Uploading files or manually transcribing just wasn't practical.

So I decided to make something that's fast.

Chapters

The problem: hearing something and losing it