GPT-Live dumps cascading speech pipelines for full-duplex voice
openai launched gpt-live, a full-duplex voice model that listens and speaks simultaneously to reduce latency and enable natural interruptions, powering a new chatgpt voice mode.
openai introduced gpt-live, a new voice model family built on a full-duplex architecture that listens and speaks simultaneously, ending the trade-offs of cascaded systems that chained stt, llm, and tts models. gpt-live can handle interruptions, back-channeling like 'mhmm', and delegate complex reasoning to gpt-5.5 in the background without halting the conversation flow. the rollout includes gpt-live-1 and gpt-live-1 mini for chatgpt voice, with api access coming later. this shift moves ai interaction toward fluid, human-like conversation suitable for complex, long-running agentic workflows.