ClawVoice for OpenClaw vs HopPT

ClawVoice, formerly iClawd, is a voice-first companion for OpenClaw. Connect to your own OpenClaw gateway and talk to your self-hosted agent from your iPhone, with hands-free CarPlay support for the road. Talk to OpenClaw Naturally Use voice or text depending on the moment. In voice mode, ClawVoice listens, detects when you pause, sends your prompt, waits for the agent, plays the answer, and returns to listening when hands-free mode is active. You can pause the mic or stop playback at any time. Built for CarPlay ClawVoice brings your OpenClaw agent into CarPlay with a simple driver-friendly voice interface. Start voice mode, listen for responses, and stop audio without reaching for the full phone UI. Bring Your Own Agent ClawVoice connects directly to your OpenClaw gateway. Use your own server, VPS, Tailscale setup, or reachable gateway URL. Your agent, your infrastructure, your control. Text Chat When You Need It Prefer typing? Use the chat screen for regular text prompts, streaming responses, and quick follow-ups. The mic in chat mode works as dictation, so you can speak into the input, review the text, then send manually. Better Voice Options Use Apple’s built-in speech tools, or add your own ElevenLabs API key for more natural text-to-speech and optional speech-to-text support when available. Siri Shortcuts Add a Siri shortcut to jump into voice mode faster. Notifications and Background Audio Get notified when your agent responds, and let ClawVoice continue playing agent responses while the app is in the background when supported by your device settings. Privacy and Control ClawVoice does not collect prompts, messages, transcripts, audio, gateway URLs, auth tokens, or API keys. Credentials are stored locally on your device. Minimal usage analytics can be disabled in Settings. Open Source ClawVoice is open source and built for the OpenClaw community.

HopPT offers a complete chatbot experience for any LLM API provider. It is also great to access your local models. The web search functionality uses serper.dev for searching, but the whole pipeline runs on your device. Your conversations are just between you and your LLM. We are very proud of the web search performance. Instructions: -Add an endpoint in settings (with API Key if required). -Press Manage Models, select the models from that endpoint that you want to be able to see in the model selector. -If you want to use web search, add your serper.dev API Key. -For a very slight improvement in web search answer quality (but a slight hit on context window and speed) you can add a jina.ai API Key to outsource the url scraping to Jina Reader. We recommend using the local WebKit solution. For an optimal web search experience we advise not to use thinking models when you enable the web search functionality. We also advise to use web search with models that are faster than 20 tokens per second in token generation and 200 token per second in prompt processing speed (web search context is on average 8k tokens, but it can reach 30/40k for complex searches). The app also has a fully local whisper-v3-large-turbo model that the user has to download and compile in settings. It will stay compiled throughout sessions without occupying RAM space. The transcription functionality is a super cool thing by itself. It's 15x faster than real life speed and is fully local. You can try a voice-only bonus functionality (for better voice quality download premium voices on your iPhone's settings)