Turn speech into text.Privately, for free.
Bulk transcribe audio and video files, one after another, without uploading anything. Export every result as TXT, SRT, or VTT. Free forever and built courtesy of RapidXAI.
Everything stays local on your device. The first job downloads and caches the private browser engine, so later jobs can work offline. Large batches and longer recordings take more time, but no file or transcript is sent to a server.
Best default for multilingual speech. Uses modest memory and usually runs comfortably on recent laptops and phones.
What happens when you start: your browser downloads the selected speech model from its public model host, then caches it on this device. Your audio, video and transcript are never uploaded. A larger model can improve difficult speech, but it uses more data, memory and time and cannot guarantee a perfect transcript.
Idle
This can take a moment — play a round of Snake while you wait
Arrow keys / WASD, or swipe on mobile.
Why ScriptFlow
100% private
Your file never leaves your device. There is no server to send it to.
Free, no account
No sign-up, no API key, no usage limits. Ever.
TXT, SRT & VTT
Export plain text, or timestamped subtitles for video editors and players.