Choose a recording
Add a supported audio or video file, or record directly from your microphone.
Use browser-based Whisper to convert local audio and video into editable text across 99 supported languages, with no account or recording upload.
Choose from the complete Whisper language list or let the tool detect the spoken language automatically. Support includes English, Spanish, Chinese, Arabic, Hindi, Japanese, Russian, Vietnamese, and many more.
This tool uses the open-source Whisper speech recognition model to transcribe audio and video locally. LocalScribe is not affiliated with OpenAI.
Your file stays private and is processed on your device.
Fast transcription is selected by default.
Add a supported audio or video file, or record directly from your microphone.
Select the spoken language or use automatic detection, then follow the progress on screen.
Correct the text and save it as TXT, SRT, or WebVTT subtitles.
LocalScribe runs the open-source Whisper speech-recognition model on your device through your web browser. It is an independent product and is not affiliated with OpenAI.
Your browser decodes the recording and performs speech recognition locally instead of sending it to our transcription server.
Transcribe English and multilingual recordings with automatic or manual language selection.
Use Whisper online without uploading your selected audio or video recording to LocalScribe.
Review the output and save plain TXT or timestamped SRT and WebVTT files.
Your selected recording and completed transcript stay on your device. Loading the website and downloading Whisper model data still require ordinary network requests, but the transcription tool does not upload your media to our servers.
Yes. LocalScribe decodes the selected file and runs Whisper inference in a browser worker on your device. The first use downloads model data, and processing speed depends on your hardware and browser.
No. LocalScribe uses the open-source Whisper model but is not affiliated with, endorsed by, or operated by OpenAI.
Yes. There is no sign-up or per-minute fee. Your device performs the transcription work.
Fast is selected by default for quicker transcription and lower memory use. Choose Higher accuracy for important recordings when you can allow more processing time.