Transcripter Studio

Drop or select a call recording. We’ll send it to the latest trained model and stream the transcript back.

Ready

Drop audio here

MP3, WAV, M4A up to 2 hours. We’ll auto-use the latest available model.

No file selected.
Latest model active from backend runtime
Awaiting upload

Leave blank when using Audilume. If you call the API outside Audilume, provide a key (sent as an X-API-Key header) or enforce it in your proxy.

No workflow generated yet.

Transcript

Upload audio to see results.

(No transcript yet)
Duration (s)
Processing time (s)
Segments

Segments