Upload an episode or record it in the browser, and Paraphrase transcribes it with a timestamp on every word. Delete a word and its audio goes with it, or let one button propose the whole cleanup: filled pauses, false starts and the sentence you said twice.
The words are already a map of the recording. Editing them is faster than finding each one in a waveform.
What an episode needs once the microphones are off.
Record in the browser, upload the files you already have, or paste a link to audio or video.
Keep every take in one project and edit them as one transcript, so a pickup sits next to the take it fixes.
One button reads the transcript and proposes the cut: filled pauses, false starts and the sentence you said twice. It shows you what it took, and you can put back any word it removed.
Drag a word to where it reads better and its audio moves with it.
WAV or FLAC keep every sample of a lossless master. MP3, M4A and Opus are there for publishing.
The export is your recording with pieces cut out. A word you never said has no audio to come from, so it cannot appear in it.
