Volocal vs OpenKitchen

Talk to an AI assistant that runs entirely on your iPhone. No cloud servers, no API keys, no subscriptions -- just real-time voice conversations powered by on-device intelligence. FULLY PRIVATE, FULLY LOCAL Every word you say stays on your device. Volocal runs three specialized AI models directly on your iPhone's hardware -- nothing is ever sent to the internet. After downloading the models on first launch, you never need a network connection again. REAL-TIME VOICE CONVERSATIONS Speak naturally and hear responses streamed back in real-time. Volocal uses a three-stage pipeline -- Speech-to-Text, Language Model, and Text-to-Speech -- all running simultaneously on different chips inside your phone for smooth, low-latency conversations. INTERRUPT ANYTIME Change your mind mid-sentence? Just start talking. Volocal supports barge-in with hardware echo cancellation, so the microphone stays active even while the assistant is speaking. No need to wait for it to finish. NO SUBSCRIPTIONS, NO API KEYS Volocal is completely free and open source. There are no in-app purchases, no subscriptions, and no hidden costs. Download the models once (~2.3 GB, Wi-Fi recommended) and you're set. HOW IT WORKS Volocal splits the workload across your iPhone's specialized processors: - Speech recognition (Parakeet EOU) runs on the Neural Engine - Language model (Qwen3.5-2B) runs on the GPU via Metal - Text-to-speech (PocketTTS) runs on the Neural Engine This separation means all three models can run at the same time without competing for resources, keeping conversations fluid and responsive. LIGHTWEIGHT Total runtime memory usage is approximately 1.2 GB, well within the limits of modern iPhones. REQUIREMENTS - iOS 17 or later - Physical device only (Neural Engine is not available in the Simulator) - ~2.3 GB of storage for model downloads on first launch Volocal is MIT licensed and open source. Built by Fikri Karim.

OpenKitchen is a kitchen for AI, and the door is open. Most AI works behind a wall. You hand over a request, you wait, a plate comes out, and you never see how it was made or get to change it halfway. We think AI is only open when you can see into it and change it. So OpenKitchen is built around two things you can always do. GIVE THE ORDER Tell a cook what you want, by voice or by text, in plain words. Each cook is an AI agent (Claude, Codex, Gemini, Qwen or Kimi) working in a kitchen of its own: a real computer in the cloud, always on, with a terminal, a browser and a phone. Say it once. Change the order whenever you like, even while the cook is mid-task. WALK UP TO ANY COUNTER Every counter in every kitchen is open to you at any moment. Tap Preview and you are looking at the cook's own screen. Step in to set something up, clear what is blocking it, check the work, or point it somewhere new. Then step back and let it cook. On a laptop the same kitchen opens full screen, like a machine of your own. EVERY KITCHEN, AT A GLANCE The stage shows all your kitchens and every cook in them: who is busy, who has stopped and needs you, and what each one is on. As you grow, group kitchens into courts: one for a product, one for a client, one for the books. THE SOUS-CHEF When a cook stops on something small, the Sous-Chef deals with it. When the decision is yours, it calls you. You are interrupted less, and nothing that matters is kept from you. YOURS Your kitchens, your sign-ins, your data. Nothing sits in a box you cannot open. Fire a cook, close a kitchen or delete your account whenever you want. HOW IT STARTS 1. Join at openkitchen.inc. 2. Add a kitchen and hire a cook: name it and give it the order. 3. Watch the prep from this app, and step in where it matters. PLANS A kitchen starts small and scales itself when the work needs more. Mini counter from $1 a month, flex counter from $10, small kitchen from $20, medium from $40, full from $80. Let it cook.