OpenAI GPT-Live 1.1 Voice Model Available on AI Gateway
·2026.11.19 09:00
Key point
The new model supports full-duplex audio and allows delegation to other models like gpt-6.2-sol while maintaining the existing Live endpoint.
Details
- GPT-Live 1.1 is now available on AI Gateway as a full-duplex voice model that listens while speaking, allowing users to pause, interrupt, or add detail mid-reply.
- Compared to the previous GPT-Live model, version 1.1 offers more accurate speech transcription and maintains a more consistent accent and voice across languages.
- Integration requires only the new model ID (openai/gpt-live-1.1) as it uses the same Live endpoint and client delegation infrastructure.
- Client delegation allows the voice model to request help from other text models on AI Gateway, such as openai/gpt-6.2-sol, with delegated requests billed separately while voice-session usage continues.
- AI Gateway provides a unified API with no markup on provider pricing and no platform fee on inference, including Bring Your Own Key (BYOK) requests.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.