Voice
Talk to Kawase on iPhone and Android in your language; it answers aloud and shows the same cards as chat. Payments by voice always wait for your tap.
Tap the orb in the dock and speak. The page blurs, the orb rises and listens; it shows the words it heard, answers aloud, and puts the same cards on screen as chat does.
- One conversation. What you said by voice is in your chat thread, and typing picks it up where you left off.
- What was heard is always shown before anything is confirmed.
- A spoken "yes" never approves a payment. A send by voice is prepared on its card and waits for your tap and Face ID (fingerprint or screen lock on Android) — even inside your daily allowance.
- The orb shows the network: lime on mainnet, sky blue on testnet.
Languages and voices
Kawase hears all ten languages with ElevenLabs Scribe v2 (realtime). It speaks with ElevenLabs Flash v2.5 in English, Spanish, French, Portuguese, Russian, Chinese, Hindi and Arabic, and with OpenAI's speech model in Bengali and Urdu, which Flash v2.5 does not cover.
How it works
The phone joins a LiveKit room over WebRTC. Kawase's voice worker turns speech into text, runs the same agent turn as chat (same tools, same limits, same thread), and speaks the answer while the cards arrive on your screen.
Voice
What runs today
- talking to Kawase on iPhone and Android in your language: it hears you, answers aloud, and puts the same cards on your screen as chat
- one conversation: what you said by voice is in the chat thread, and typing picks it up
- a send by voice is ready on its card and waits for your tap (Face ID / fingerprint), even inside the daily allowance
Not yet
- voice in the web app (typing works there)
- choosing Kawase's voice or speed