Drop an audio or video file and get an accurate transcript — with timestamps and ready-to-use subtitles. It runs on your own box, so sensitive interviews and recordings never leave the building.
Interviews, podcasts, meetings, lectures, voice notes. Drop the file and get clean text you can search, quote, and caption.
Any common audio or video format. We extract the audio and transcribe it right here on the server.
An accurate transcript split into timestamped segments — toggle timestamps on or off.
Copy the text, or download a clean .txt or subtitle-ready .srt in one click.
The most valuable recordings are the most sensitive. Scribewright keeps them on your infrastructure.
Show notes, captions, and repurposable quotes from every episode — without a per-minute meter.
Transcribe confidential interviews without handing the audio to a third-party service.
Depositions, consults, and reviews stay on your own box — the compliance-friendly default.
Transcribe free in the browser. Upgrade for longer files, an API, and the self-host license.
No. The file is written to a temp path, transcribed, and deleted in the same request. Nothing is stored, and there's no database.
It uses an open Whisper model that handles clear speech in 99+ languages well. Heavy accents, crosstalk, and noisy audio are harder — larger models on the paid tiers improve those.
Common audio and video: MP3, WAV, M4A, FLAC, OGG, MP4, MOV, WEBM, and more. We extract the audio automatically.
Yes — the self-host license runs the whole transcriber on your infrastructure, air-gap friendly, with no per-minute cost.