Transcribe your audio and video files completely offline. All processing happens locally in your browser, keeping your data entirely private.
Free allowance: 1 file per day across features; free transcription is limited to 5 minutes per file. View pricing and limits
Download the speech model before processing. Local speech recognition runs on your device. Signing in, downloading models and optional cloud features require a connection.
The free allowance is 1 file per day across features, with transcription limited to 5 minutes per file.
Available memory and browser support affect which models will run. Larger models need more memory and take longer to download; start with a smaller model if your device struggles.
Local recognition does not require uploading your media. Choosing cloud saving or cloud processing can upload data; review those options separately.
Local speech recognition runs inside your browser using WebAssembly. Optional cloud saving and online features are separate and can upload data.
Upgrade for unlimited offline transcription. Cloud features use subscription credits.
View Plans →