Scriptivox

Scriptivox turns recorded audio and video into accurate, searchable text. For podcast work it produces a speaker-separated transcript with word-level timestamps, generates SRT and VTT caption files for video versions of an episode, and can produce an AI summary that gives you a starting point for show notes. Transcripts can be queried conversationally, which makes pulling quotes or finding a moment in a two-hour recording much faster than scrubbing audio.

It handles 20+ formats (MP3, WAV, FLAC, MP4, MOV and others) and covers 100+ languages, which matters for shows with non-English guests. A notetaker can also join remote interviews on Zoom, Google Meet or Microsoft Teams and record them directly. There’s a REST API for anyone automating an episode pipeline.

Free tier, no credit card required.