• All docs
• Quickstart
• Setup walkthrough
• Build an extension
• Voice
• Privacy and trust
• Troubleshooting

Voice

Dictation

Dictation is local speech input using the bundled Whisper model. Audio stays on the phone.

Realtime voice

Realtime voice is a public host.stream capability. The phone handles only provider-neutral PCM, transcript, state, and control frames. Credentials, model selection, prompts, tools, and provider event translation live in a backend plugin on your machine.

The bundled adapter currently uses xAI Grok Voice. Its key is stored in an owner-only muxr file on the selected computer, never in the phone, website, or relay. The provider receives microphone audio, its system prompt, tool schemas, requested tool arguments, and any tool output needed to answer. Pane-output tools can therefore send terminal excerpts when you explicitly request them.

Realtime provider usage may be billed by that provider. Set a provider budget and review its retention policy before enabling voice. Replacing the backend adapter with another provider does not require an APK rebuild when it uses the existing generic PCM or WebRTC capabilities.