• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Developers building voice agents get a single full-duplex model that avoids the latency and brittle handoffs of chained STT-LLM-TTS pipelines, plus telephony support for real phone deployments.

• postOpenAI ships GPT-Live-1, a listen-while-speaking voice model, in the APIOpenAIDevs
• postOpenAI Shares GPT-Live-1's Task Completion and Latency BenchmarksOpenAIDevs
• clipTool calling in a real-time voice model: two models, not oneJulia Turc

Checking sign-in…

Loading comments…