Speech to text
Speech to text — private Whisper transcription in your browser
OpenAI’s open Whisper models run on your GPU or CPU — up to Large v3 Turbo, which handles Slovenian well. Transcribe meetings, interviews and voice notes with live progress, click any line to jump there, correct the text and export TXT, SRT or VTT. Audio never leaves your device.
Stays on your computer — your recordings never go to the internet
The AI model downloads to your computer once on first use, then everything is processed by your browser. Nothing is uploaded to a server — not even to Hypervision. No account, no storage, no tracking.