Voysum turns audio and video recordings into editable, searchable text. Upload a meeting, interview, lecture, podcast or video file and receive a timestamped transcript that you can review, edit and search before exporting it as TXT, SRT or VTT subtitles, or timed segments as CSV.
Beyond transcription, Voysum generates AI notes, summaries, chapters and translations from the same recording, so one upload can serve several jobs: meeting notes with decisions and action items, quotable interview answers with timestamps, study notes from a lecture, or captions and draft show notes for a creator video. A set of free browser tools covers the steps around transcription, including audio extraction, subtitle conversion and transcript cleanup, with tools marked local running entirely on your device.
The service is aimed at professionals, researchers, students and creators who work with spoken material and need reliable text rather than a rough auto-caption. The free plan covers 120 minutes per month, up to 3 files per day and 30 minutes per file, with uploads up to 100 MB and no credit card required for a first transcription; paid monthly and yearly plans add more minutes for heavier use.