Have the phone read a reply.

Tap Read aloud and that reply starts. Tap it again, now labelled Stop reading, and it stops. Starting another reply stops the one that was going. A line of sound sits on the message while it speaks, so you can see which turn is the one in the air.

The voice is the phone’s speech engine. It is separate from Speak on the website, which is a recording made on our side. Here the audio never leaves the handset, and a reply with nothing but markup left after cleaning is skipped.

Settings has “Read replies aloud”. On, each finished reply speaks by itself, and it takes the speaker if something else was already being read. Off, only the button starts it, and a new reply leaves a reading you started alone. The choice is kept on the phone between launches, next to the haptics switch. Haptics are the small taps on buttons and tabs. They are independent of the voice.

Speech starts when the reply has landed, not one token at a time while it is still streaming.

The button is on assistant messages. Your own turns stay text. Code fences lose their fence marks and are read as the words inside, which is useful for a short snippet and noisy for a long one. For a long one, copy is the other action on the same row, and it keeps the original Markdown.