OpenAI Launches GPT-Live-1 API for Full-Duplex Voice Conversations

OpenAI has introduced the GPT-Live-1 full-duplex voice model in its API, enabling simultaneous listening and speech generation. This improvement enhances handling of interruptions, pauses, background noise, and extended conversations, making it suitable for telephone scenarios. Developers can control tone, speech rate, and conversation style through system prompts, delegating deep reasoning and tool invocation to backend text models like GPT-6 Astra or third-party models. GPT-Live-1 shows a 30 percentage point improvement over GPT-Realtime-2.1 on the Full Duplex Bench; early tests from the language learning platform Speak indicate that this model reduces misinterruptions of learners' thinking pauses by nearly 80% compared to traditional turn-taking systems. The GPT-Live-1 API is now available, with front-end voice layer pricing set at $0.05 per minute, while backend model and agent framework costs are additional.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.