What Scribewren does

Upload audio or video and get a transcript you can read against the audio, fix, export and build on. Each feature below has its own page.

Transcription

Upload a recording and get a transcript with timestamps, punctuation and speaker labels. Read it back against the audio, fix it and export it.
Speaker identification

Scribewren separates the voices in a recording and labels each turn as Speaker 1, Speaker 2 and so on. Rename a speaker once and the name applies everywhere.
Transcript editor

Read the transcript with the audio beside it. Click any word to hear it and fix what the model got wrong. Your edits save as you type.
Subtitles and exports

Export a finished transcript as TXT, DOCX or PDF, or as SRT and VTT subtitles. Timestamps and speaker names are options you choose each time.
AI notes

Generate a summary, chapters or action items from a transcript when you ask. Chapters and action items link back to the moment in the audio.
Translation

Translate a finished transcript into another language. Timing and speakers are kept, so you can export translated subtitles too. Included in Unlimited.
Privacy and retention

Original files are deleted within 24 hours of the transcription finishing. Playback copies are kept for a fixed time. Nothing you upload is used to train models.
API and webhooks

Upload recordings, follow each transcription and fetch transcripts from your own code. Signed webhooks tell you when a job finishes. Included in the Unlimited plans.

Try it on your own recording

Free includes a few transcriptions a day. No card needed.