Speech to Text
Good words. Ready to edit.
Drop in a recording, get a transcript, and download captions for your next video.
Files stay on your device. Nothing is uploaded.
Ready when you are.
Drop your file here
MP3 · WAV · M4A · MP4 · WebM
Up to 200 MB or 30 minutes. Format support depends on your browser.
Whisper Base · about 80–210 MB per language option, depending on your device. Models are cached after first use. First use also downloads a shared 22 MB runtime.
Your transcript
Click any line to edit.Give it a quick read before you post. AI can miss words, especially with music or overlapping voices. Voiceovers are in English for now.