← Chat features

Voice & TTS

A full voice mode, with the model you chose.

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.

Mic button for speech-to-text in the composerSpeaker button on assistant repliesVoice mode keeps your selected text model activeGenerated audio is saved in Files for 30 daysAvailable on Studio and above

Voice inside the chat surface

Speak.Listen.Continue.

The mic, the speaker, and voice mode are all part of chat, so you can use voice without leaving the conversation.

Speech in. Reply out. Same thread.
Audio-native in chatGPT audio mini

Choose it as the chat model for audio-native replies.

OpenAI read-aloudGPT-4o mini TTS

Playback model used from Voice settings.

Grok read-aloudGrok Voice

xAI playback model, selectable in Voice settings.

ElevenLabs read-aloudElevenLabs Flash v2.5

ElevenLabs playback model, selectable in Voice settings.

How it works in product

Three ways to use voice, depending on what you need right now.

Use the mic for faster input, the speaker for playback, or voice mode for a hands-free conversation.

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.

Speaker button

Hear a reply read aloud.

Assistant replies keep a speaker action right on the message, so you can listen without leaving the thread.

Voice mode

Turn on voice mode for hands-free chat.

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

Voice models available today.

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

OpenAI chat audio models

Select one of these as the chat model for audio-native replies.

GPT audio minigpt-audio-mini
GPT audio mini · Dec. 2025gpt-audio-mini-2025-12-15
GPT Audio 1.5gpt-audio-1.5

OpenAI read-aloud

OpenAI playback models

Selectable in Voice settings for reply playback and previews.

GPT-4o mini TTS (2025-12-15)gpt-4o-mini-tts-2025-12-15
GPT-4o mini TTS (2025-03-20)gpt-4o-mini-tts-2025-03-20
GPT-4o mini TTSgpt-4o-mini-tts

Grok read-aloud

xAI playback model

Selectable in Voice settings for Grok read-aloud.

Grok Voicegrok-tts
11

ElevenLabs read-aloud

ElevenLabs playback model

Selectable in Voice settings for ElevenLabs read-aloud.

ElevenLabs Flash v2.5eleven_flash_v2_5

Voice settings

Set your voice preferences in Account.

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.

Text modelYour selected text model stays selected

Voice mode uses the chat model you selected.

Read-aloud modelOpenAI, Grok Voice, or ElevenLabs playback

The read-aloud model is set separately from the chat model.

Voice settingsProvider voices, OpenAI styles, silence timing, thinking sound, playback speed

These controls are in Voice settings in Account.

OpenAI voice styles
NeutralWarmExpressiveCalmStoryteller

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

Generated audio is saved to Files for 30 days.

Read-aloud and voice-mode audio is stored in Files under Generated Audio for 30 days, where you can find and replay it.

Files / Generated Audio

Voice-mode and read-aloud audio is saved to the Generated Audio area of Files.

Saved in Files under Generated Audio
Kept alongside the rest of your generated media
Available to replay for 30 days

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.