Mic button
Speak straight into the composer.
Tap the mic and just4o.chat starts speech-to-text inside the chat box itself, so you can dictate a message instead of typing it.
Voice & TTS
Tap the mic to speak into the composer. Tap the speaker on any answer to hear it back. Turn on voice mode and just4o.chat can auto-send the transcript after your silence window, read replies aloud when they land, and keep the whole exchange inside the same chat, with your selected text model still doing the thinking.
Voice inside the chat surface
The mic, the speaker, and voice mode are all part of chat, so you can use voice without leaving the conversation.
Choose it as the chat model for audio-native replies.
Playback model used from Voice settings.
xAI playback model, selectable in Voice settings.
ElevenLabs playback model, selectable in Voice settings.
How it works in product
Use the mic for faster input, the speaker for playback, or voice mode for a hands-free conversation.
Mic button
Tap the mic and just4o.chat starts speech-to-text inside the chat box itself, so you can dictate a message instead of typing it.
Speaker button
Assistant replies keep a speaker action right on the message, so you can listen without leaving the thread.
Voice mode
With a silence window configured, transcripts can auto-send, replies read aloud when they finish, and the whole exchange stays inside the same chat.
Available voice models
Your selected text model stays active in voice mode. Several of these voice models are scheduled to retire in January 2027. See the deprecation calendar for current dates.
Audio-native chat
Select one of these as the chat model for audio-native replies.
OpenAI read-aloud
Selectable in Voice settings for reply playback and previews.
Grok read-aloud
Selectable in Voice settings for Grok read-aloud.
ElevenLabs read-aloud
Selectable in Voice settings for ElevenLabs read-aloud.
Voice settings
Voice settings are in Account. Choose the read-aloud model, pick a voice, adjust the silence window, switch the thinking sound on or off, and set playback speed.
Voice mode uses the chat model you selected.
The read-aloud model is set separately from the chat model.
These controls are in Voice settings in Account.
Using OpenAI voices
Set read-aloud to GPT-4o mini TTS for OpenAI playback voices. For audio-native replies, switch the chat model to GPT audio mini.
Saved in Files
Read-aloud and voice-mode audio is stored in Files under Generated Audio for 30 days, where you can find and replay it.
Voice-mode and read-aloud audio is saved to the Generated Audio area of Files.
Use voice in the chat you already have.
Open chat, speak into the composer, and turn on voice mode when you want a hands-free conversation.