Voice Mode on your phone

Voice Mode turns one session into something you listen to. When it is on, the Wingman narrates each completed turn as spoken audio, and you answer by talking. It is the middle ground between reading the Chat view yourself and going fully hands-free with Car Mode.

Turning it on

Open a session and pick the Voice mode tab, then tap Switch to voice mode. From then on the session shows up on the roster with a voice indicator, and every finished turn produces a narration clip.

Listening

While the agent works, the screen shows Agent is working...; when a turn completes, the Gateway generates the narration and your phone downloads it before offering playback - so when it says ready, it plays instantly. A fresh clip plays automatically while you are on the screen, with a full player: play/pause, restart, and a seek bar. Leave halfway through and it resumes where you stopped. If the agent starts working again, the old narration is retired - you never act on stale news.

• Respond - answer by voice. Speak, review the transcript at Pause if you want, then Send. The reply transcribes and submits in the background.
• Regenerate response - rebuild the narration for the current turn.
• Generate narration now - if no clip is ready, ask for one on the spot.
• Turn voice off - back to a normal session.

AI settings

The AI settings screen (in the menu) controls the voices and models behind all of this - for your whole fleet, not just this phone:

• Thinking model - answers when you talk to the Wingman and ask product questions.
• Fast model - spoken turn summaries and menus.
• Car Mode model - drives Car Mode.
• Speech model and Voice - how narrations sound, with a Play sample button.
• The transcription model is shown read-only.

Each model row has a Test button so you can check a choice before living with it. Hosted models bill from your prepaid credits like everything else - see hosted vs bring-your-own key.