VoiceClaw Realtime vs Local LLM

VoiceClaw Realtime turns your iPhone, iPad or Apple Watch into a continuous live AI voice interface, using GPT Live and GPT Realtime voice models to chat with you, control AI agents running on your Mac or PC, take on-device actions on your iPhone or iPad, and operate your computer, all with your existing ChatGPT subscription. Talk naturally, interrupt at any time, and keep one continuous AI voice conversation going while you start, monitor, steer, and switch among simultaneous underlying AI agent workstreams and control your device. QUICK START Talk naturally with GPT Live or GPT Realtime. Use Voice Only for conversation, or choose GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Sol, or GPT-6.1 Terra in GPT Direct for deeper reasoning behind the scenes. Select your route by voice or from the main screen. YOUR AI AGENTS When you’re ready to control computer-side AI agents from your iPhone, iPad, or watch (including over cellular connections when you're away from your computer), install the free private desktop Companion app. Instantly pair your device using the desktop Companion app's private QR code to start controlling your Codex, OpenClaw, and Hermes AI agents on your computer without ending the live voice session. Your connection is made possible through either your free, private, device-to-device Tailscale connection or an optional free personal HTTPS tunnel. DO REAL WORK Start concurrent tasks, steer follow-ups, monitor statuses, resume recent sessions, and receive generated files in the app. Your computer-side AI agents automatically use all of their existing capabilities without any additional setup. FILES AND MEDIA Attach photos, files, or camera captures using your voice or the Live screen's attachment button to get instant analysis or to send them to your agents. Get files back from your Codex / OpenClaw / Hermes agents and view / download them within the app: just tell VoiceClaw Realtime to ask your agents to send the files they create (or files already on your computer) to VoiceClaw Realtime. The files stay on your Mac/PC and are sent directly to your device via your private Tailscale connection or optional personal HTTPS tunnel. View your inbox contents at any time, including from past VoiceClaw Realtime sessions. HANDS-FREE CONTROL Ask VoiceClaw Realtime to read your screen, draft messages and emails, navigate Maps, browse the web, read your screen, change in-app settings, switch routes, mute the mic, and more. Keep the mic on in the background to keep the conversation going, or keep the mic muted until you're ready to resume. LIVE TRANSCRIPTS View live captions of your conversation, including in-transcript updates of AI agent handoffs, task progress, completed work, and received files. NOTIFICATIONS, ACTION BUTTON, WIDGETS, and SMART STACK See agents' live status with iOS Live Activities and get notifications when agents finish working. Activate VoiceClaw Realtime with the Action Button. Add Home Screen widgets for quick access to your favorite voice routes and agents. Open VoiceClaw Realtime on your watch from the Smart Stack or with the double-tap gesture. PRIVACY AND OWNERSHIP VoiceClaw Realtime uses your own existing ChatGPT subscription (or an optional OpenAI API key) and your own computer and network setup. Credentials stay in your device Keychain or Companion configuration. The app doesn't contact any third-party servers, or even our own (we don't have any)! We can't see your conversation or credentials; they stay with your device, your computer, and your AI model provider. The app itself checks only one URL — https://www.voiceclawrealtime.com/companion — to check if a new version of the desktop Companion app is available and notify you to download it. Privacy Policy: https://www.voiceclawrealtime.com/privacy/ Support: https://www.voiceclawrealtime.com/support/ Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Local LLM runs language models on your iPhone. No account is required. Chat, ask about photos, work with documents and use live voice. With Canvas, build websites, interactive pages and games from a conversation, then preview and edit them in the app. Features depend on the selected model. Download models from the catalog, or use Apple’s on-device model on supported devices when available. Core AI models require iOS 27 or later. Other supported models remain available on older systems. Inference and conversation history stay on your device. Model downloads, the catalog and model artwork use the network. Optional Web Search sends a query derived from your message to Tavily and may read result websites. Weather requests use Apple geocoding and WeatherKit for the requested city, without requesting device location. Voice input prefers on-device recognition. If it is unavailable or fails, Apple’s online speech service may process audio when network speech recognition is enabled. You can disable this in Privacy settings. Requires iOS 17 or later. Model availability depends on your device, OS, memory and storage. Downloads require internet; supported offline chat works after setup. Models can make mistakes. Do not rely on replies for medical, legal or financial decisions.