Voice to Text
whisper-small running entirely in your browser — no server, no api key, stays on your device.
⏳ loading whisper-small model (~460mb) — first visit only, then cached…
record
⟳ transcribing…
or upload a file
drop an audio file here, or click to browse
supports mp3 · wav · ogg · m4a · webm
transcript
supports mp3 · wav · ogg · m4a · webm
note: the model runs locally in your browser via WebAssembly.
first load downloads ~460mb (cached after that). processing a 1-min clip takes
~15–60 seconds depending on your device. works fully offline after first load.