Settings

Storage

Checking…

Default behavior on this device

Heavy tools

These tools download additional model files on first use. On mobile or metered connections, you can control which ones cache automatically.

OCR 10 MB

Extract text from images using optical character recognition.

disabled

Detect every face in a photo and blur it — runs entirely on your device.

disabled

Upscale low-quality audio to clean 48 kHz. Great for cleaning up phone recordings, Zoom calls, or old podcasts.

disabled
Speech tools (Whisper, future TTS) 250 MB

1 speech tool (Whisper-tiny for transcription). Downloads ~250 MB on first use — runs entirely on your device.

disabled
Vision tools (image captioning) 350 MB

2 image-to-text tools (caption / describe / extract). Downloads ~350 MB on first use — runs entirely on your device.

disabled
gdal 40 MB

Tool group: gdal. Downloads ~40 MB on first use.

disabled
Audio/Video tools (ffmpeg) 960 MB

32 audio and video conversion tools powered by ffmpeg.wasm. Downloads ~30 MB on first use.

disabled
Image AI tools 359 MB

4 AI-powered image tools (background removal, upscaling, OCR Pro, image similarity). Downloads ~359 MB on first use — runs entirely on your device.

disabled
NLP tools (sentiment, NER, summarize, embeddings) 278 MB

4 natural language processing tools. Downloads ~278 MB on first use — runs entirely on your device.

disabled
Text translation (M2M100) 400 MB

Translation model (400 MB). Only needed as a fallback — Chrome 131+ and Firefox use their built-in translator automatically.

disabled

"Enabled" means this tool's model will be cached when you use it. Actual cache contents and total disk usage are shown in the Storage panel above; clear them there.