GPT-Live — Real-Time Voice AI
GPT-Live is OpenAI's full-duplex voice model that listens and speaks simultaneously for natural, real-time conversations. It powers ChatGPT with interruption support, background task delegation to frontier models, and 9 distinct voices — making AI interaction feel like a real dialogue.
Powered by Gemini 3.5 Live Translate · Real-time speech-to-speech translation for 70+ languages
All Tools
Browse AI tools
Free AI Video
100% Free AI Video Generator
Free GPTImage2
Best Image Generator
Seedance2.0
The Future of AI Video Is Here.
Free AI Image
Truly Free AI Image Generator
Gemini Omni
Gemini Omni Video Generator
Veo3.1
Create Stunning Videos with Veo3.1
Kling3
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
100% Free AI Video Generator
100% Free Image Generator
Seedance 2.0 AI Video Generator — The Future of AI Video Is Here
Gemini Omni Video is Here
Kling 3 Is Here
Kling 3 - See the Sound, Hear the Visual.
AI Video Effects
AI Effects - Create Funny Videos Easy!
GPT-Live — Full-Duplex Voice AI for Natural Conversations
OpenAI's next-generation voice model built on full-duplex architecture. It listens and speaks simultaneously, supports interruptions, delegates complex tasks to frontier models, and delivers lifelike conversations with 9 distinct voices — designed for real-time, natural AI interaction.
- Full-Duplex VoiceIt processes input and output simultaneously, making interaction decisions multiple times per second for fluid, natural back-and-forth.
- Background Task DelegationHands off complex tasks like search and deep reasoning to GPT-5.5 while continuing to converse, keeping the flow uninterrupted.
- Natural Voice InteractionsOffers 9 newly crafted voices, uses natural filler words, and never interrupts — making every conversation feel human and responsive.
Why Use GPT-Live
This full-duplex voice AI transforms interaction with simultaneous listening, speaking, interruption support, and background task delegation. Ideal for daily assistance, language practice, storytelling, commuting, and real-time translation.
GPT-Live Capabilities
GPT-Live brings full-duplex voice AI with simultaneous listening and speaking, background task delegation, 9 expressive voices, and rich visual responses — designed for real-time natural conversations.
Full-Duplex Conversations
It processes input and output simultaneously, making interaction decisions multiple times per second for smooth real-time dialogue.
Frontier Model Delegation
Routes search, deep reasoning, and code tasks to GPT-5.5 in the background, maintaining conversation without interruption.
9 Distinct Voices
Offers 9 newly crafted voices with unique personalities, natural expression, and lifelike intonation for every conversation.
Visual Information Cards
Shows rich card-style visuals for weather, stocks, sports, and more alongside voice replies for at-a-glance understanding.
Multi-Platform Support
Rolls out across iOS, Android, and ChatGPT.com with GPT-Live-1 for paid users and GPT-Live-1 mini for free users.
GPT-Live — Frequently Asked Questions
Common questions about GPT-Live's capabilities, availability, and access on ChatGPT.
What is GPT-Live?
OpenAI's full-duplex voice model that listens and speaks simultaneously, supports interruptions, and delegates complex tasks to frontier models like GPT-5.5.
How is GPT-Live different from standard voice mode?
GPT-Live uses full-duplex architecture for simultaneous listening and speaking, supports background task delegation, and feels like a real conversation rather than turn-based interaction.
What models power GPT-Live?
GPT-Live-1 powers ChatGPT Go, Plus, and Pro. GPT-Live-1 mini powers the free tier. Complex tasks are delegated to GPT-5.5 in the background.
How do I access GPT-Live?
GPT-Live is rolling out globally on iOS, Android, and ChatGPT.com. Free users get GPT-Live-1 mini; paid users get full GPT-Live-1.
What can GPT-Live do?
GPT-Live handles natural conversations, language practice, storytelling, commuting chat, real-time translation, and displays visual cards for weather, stocks, and sports.
Does GPT-Live support video or screen sharing?
Not at launch. Standard voice mode and advanced voice mode remain available. Video and screen share support is planned for future releases.
Try GPT-Live Today
Experience GPT-Live's full-duplex voice AI — speak naturally, interrupt anytime, and get smarter answers with background task delegation. Available now on ChatGPT.