GPT-Live-1
GPT-Live-1 is OpenAI's full-duplex voice model for real-time spoken conversation. The API ID is gpt-live-1.
Provider
OpenAI
Model family
OpenAI GPT-Live
Full-duplex voice model
Cost tier
Live 1
Status
Current
Release Jul 8, 2026
Why teams choose it
This is the conversation front-end, not an ASR-only model
Muse Voice Transcribe and Gemini 3.5 Transcribe return text; GPT-Live-1 speaks.
API card: $0.05 per minute billed per second
Concurrent-session limits by usage tier. Free API tier is not supported.
GPT-Live-1 mini is the ChatGPT free-tier voice default in the system card
There is no gpt-live-1-mini API model card; do not invent one.
Tradeoffs to know
- Image and video are not supported on the API card. Structured outputs and fine-tuning are not supported.
- The live model has a small context window. Put tools and business rules in the backend prompt.
- Interrupting speech does not automatically cancel delegated backend work.
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Technical specs
- Inputs
- audio, text
- Outputs
- audio, text
- License
- Proprietary API
- Knowledge Cutoff
- 2025-07-31
- Session Price Per Minute Usd
- 0.05
- Capabilities
- full-duplex voice
- speech-to-speech
- streaming ASR transcripts
- interruption handling
- turn detection
- keyword biasing
- backend delegation
Sourcehttps://developers.openai.com/api/docs/models/gpt-live-1
Related models
OpenAI
GPT-5.5
OpenAI's current flagship model for complex reasoning, coding, and professional work, documented in the OpenAI API mo…
OpenAI
GPT-5.4 nano
OpenAI's smallest GPT-5.4 nano model, documented in the official OpenAI API model guide for very low-latency or econo…
OpenAI
GPT-5.4 mini
OpenAI's smaller GPT-5.4 mini model, documented in the official OpenAI API model guide for lower-latency or lower-cos…
GPT-Live-1 FAQ
What is GPT-Live-1?
GPT-Live-1 is OpenAI's full-duplex voice model for real-time spoken conversation. The API ID is gpt-live-1. It listens and speaks at the same time, handles interruptions, and delegates reasoning and tool use to a backend agent instead of doing that work itself. OpenAI's system card (July 8, 2026) introduced it as the paid ChatGPT voice default. The API launch post (September 10, 2026) documents Live sessions, native ASR transcripts and response text, keyword biasing, and turn detection. Voice sessions are billed $0.05 per minute, per second. Backend model and tool usage is billed separately.
When does GPT-Live-1 fit best?
Voice agents that keep talking while a backend looks something up
What should teams watch out for with GPT-Live-1?
Image and video are not supported on the API card. Structured outputs and fine-tuning are not supported.
Explore next
Models, tools, and comparisons that connect to this reference.