MLX vs Super Fast Local Transcribe

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.

Tap one button, speak, and watch your words appear. SFLT turns speech into text entirely on your iPhone, on the Neural Engine. Nothing is uploaded. There is no account, no subscription and no per-minute bill. You buy it once. LIVE TEXT, HONESTLY Words arrive while you are still talking. Settled words are solid; the last few seconds are dimmed, because the model may still change its mind about them. When you stop, a final pass over the whole recording produces the transcript that gets saved. EVERY WORD IS TIMED Audio and transcript are kept together, with a timestamp on every word. Play a recording back and the text follows along. Tap any word to jump to that moment. SEND IT ANYWHERE Export plain text, SRT subtitles, the M4A audio, or audio and text together, through the normal iOS share sheet: Mail, Messages, Signal, WhatsApp, AirDrop, Files, Shortcuts. No integrations of ours. No server of ours. A LIBRARY, NOT AN ACCOUNT Every recording is a folder on your phone holding the audio, the transcript and its title. Rename it, share it, delete it. Nothing to sign in to, nothing to sync, nothing to cancel. 25 EUROPEAN LANGUAGES Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian. NOTHING LEAVES THIS IPHONE The app makes exactly one kind of network request, ever: it downloads the speech model once, during setup. After that it works in airplane mode permanently, which is the easiest way to check the claim yourself. No analytics, no crash reporting, no advertising identifier, no account. BEFORE YOU BUY iPhone only, portrait, iOS 18 or later. Setup downloads a 467 MB model once, best over Wi-Fi. Transcription is a machine reading your voice, so it makes mistakes; the transcript is a draft, not a record. Made by Run Labs in Vienna. Speech recognition by Voz from Desert Ant Labs, built on NVIDIA Parakeet TDT 0.6B v3 (CC BY 4.0).