Transcribe media collections into searchable archives
Transcribe audio and video collections with consistent metadata, timestamps and exports. Build a searchable text archive of your media.
Availability depends on the configured speech provider.
Guest preview: up to 50 MB and 10m. Results are kept for a limited time unless you create an account.
Archives, newsrooms and production teams accumulate media faster than anyone can watch it. Transcribing each file turns the collection into text you can search by phrase and jump into by timestamp.
Every transcript keeps its provenance: the provider and model used, the original text, and the history of edits.
What you get
- Transcripts with provider and model provenance
- Timestamps for locating moments inside long files
- JSON and CSV exports for cataloguing systems
- Private storage with workspace isolation
Who it is for
- Newsrooms indexing raw footage
- Production companies logging interviews
- Organizations preserving oral histories
Frequently asked questions
Can I search across all my files?
Yes. The Knowledge Library searches every transcript in your workspace by phrase, scoped by collection or tag, and each result jumps to the timestamp where it was said.
What metadata is kept?
Original file name, duration, format, detected language, provider and model, plus the full revision history.
Is there a bulk upload?
Batch processing is planned. Today each file becomes one project.