MLX vs FrankenOCR

MLX-Serve is a private AI studio that runs entirely on your iPhone. Every conversation, voice recording, and generated image is processed on-device by open-weight models — nothing you type, say, or create ever leaves your phone. There is no account to create, no subscription, and no tracking of any kind. MUSIC Generate songs locally using your device ! You can also play it back in the background and use MLX-Serve as a player for your generated music on the go. CHAT Talk with capable open language models (Google Gemma 4) right on your device. Ask questions, brainstorm, draft messages, get things explained. Some models can even understand photos you attach. CALL Tap Call inside any conversation to talk to the AI hands-free, like a phone call. Your speech is transcribed on-device and the reply is read back aloud. Speaker and handset modes are both supported, and the transcript is saved to your chat. VOICE CLONE Record about eight seconds of your voice and have the AI speak text in your own voice, using an on-device text-to-speech model. Great for narration and fun. IMAGES Generate images from a text prompt with an on-device diffusion model (FLUX.2). Tap a result to zoom in, save it to your photo library, or share it. FULLY PRIVATE, FULLY OFFLINE - Runs 100% on-device using Apple MLX and the Metal GPU. - No account, no analytics, no ads, no tracking. - The network is used only to download the AI models you choose from Hugging Face. After a model is downloaded, that feature works offline. REQUIREMENTS Models are multi-gigabyte downloads and on-device AI is demanding, so MLX Chat requires a recent, high-performance iPhone. Download over Wi-Fi is recommended. You pick which models to download and can delete them anytime to reclaim space. Open models are provided under their respective licenses (Gemma, Apache 2.0). MLX Chat is an independent app and is not affiliated with Google or Apple.

Extract text from an image or scanned PDF without uploading the document. FrankenOCR uses the same pure-Rust Unlimited-OCR engine as the FrankenOCR command-line project. Choose a photo, file, camera capture, tall scrolling screenshot, or scanned PDF. The app reads the input in memory and produces structured Markdown on the device. The flagship recognition path uses a downloaded, verified Baidu Unlimited-OCR model for careful document extraction. Tall screenshots are divided with overlap-aware smart cuts, while PDF pages are processed as a document and low-yield pages are called out instead of silently disappearing. Live Camera mode uses Apple's on-device Vision text recognition for speed. It is less accurate than the flagship FrankenOCR model, and the app labels that tradeoff clearly. Recognized words flow from their camera positions into the capture tray as the view updates. The current app ships one flagship model: Unlimited-OCR. It does not claim to include GOT-OCR2, SmolVLM2, OneChart, or a music-recognition model. Images, PDFs, camera frames, and recognized text stay on the device. Network access is used only to download the static flagship model files.