Voice - Cortex Docs

Chat has two voice controls: a mic in the composer for dictation, and Listen under each answer to hear it read aloud. Each appears only when the deployment behind it can actually do the work.

A Chat reply with a syntax-highlighted Python code block and the Copy and Listen controls beneath it — Under every reply: Copy, Listen, and feedback. Listen is present because this deployment can speak.

The controls

Control	Where	Appears when	What it does
Mic	In the composer	The deployment can transcribe	Turns speech into text in the composer; you still press Enter to send
Listen	Under an answer	The deployment can speak	Reads the answer aloud

If a control is missing, that capability is switched off for this deployment. There is nothing to configure on your side, and it is not a broken button.

Language

English is the source of truth for spoken and written copy. The interface can be localized under Settings → General → Language; model prompts stay in English. See Settings.

Streaming — answers arrive as text before you can listen to them.
Troubleshooting — what missing controls mean.

⌘I