AI transcription with speaker names and caption publishing
Upload audio and get an editable transcript with speaker labels, then publish it to your feed as a caption track.
Episodes can be transcribed automatically once the audio is uploaded. The transcript opens in an editor where you fix wording, map each detected speaker to the person who was actually talking, and publish the result to your RSS feed as a caption track.
- Turn auto-transcribe on for a whole show, or run it on a single episode
- Map detected speakers to the people already credited on the episode
- Export as SRT, VTT, plain text or JSON
- Publish a caption track that podcast apps can read