Transcribed, speakers included.
Automatic transcription separates the voices, runs in France and has no length limit. Manual entry stays free.
Who’s speaking
Automatic transcription separates the voices and numbers them. You name them once, and every line of the text carries the right name.
Separated automatically
Voices are told apart during generation and arrive numbered: Speaker 1, Speaker 2, as many as there are.
Name them once
You type “Noé” or “Camille,” and the name replaces the label throughout the episode. A name left blank hides the label.
Fix what slips through
A jingle counted as a speaker, two voices mixed up: the menu on each line reassigns whatever was split wrong.
How it arrives
Launched from the Audio Studio, the transcription runs in the background. Processing takes place in France, however long the episode.
One token per minute
Starter includes 100 per month, Pro 500, Studio 1,500. Unused tokens carry over once. Packs start at €12, and purchased tokens stay with you.
Or by hand
Every episode has its own transcript field, even on the Free plan. Just paste the text you already have.
Carried over on import
If the feed you import already contains transcripts, their text is carried over and shows under each episode.
Where it’s used
Below the episode, in an expandable block. And in your feed, for apps that can display it during playback.
On your site
The text appears below the episode in an expandable block, even on the Free plan, and search engines read it.
In listening apps
A generated transcript goes into your feed as VTT, timed and with speaker names: Apple Podcasts shows it during playback if you choose your own transcripts in Podcasts Connect. A transcript pasted by hand shows on your site. SRT and VTT export available.
Clickable chapters
The chapters you write in the Audio Studio become clickable in your site’s player, and go out in your feed.
Manual entry for free, automatic transcription from €12/month
See all plans