OpenAI engineer confirms gpt-live-1 is full-duplex audio with no separate voice isolation model
pbbakkum · x · 2026-10-15
An OpenAI engineer confirmed that gpt-live-1 does not run voice isolation in front of the model, and that it is truly full duplex with a constant stream of input and output audio—responding to Trelis Research's speculation that a Krisp-like noise isolation model was being used to handle background speakers.
Related event: OpenAI Engineer Confirms gpt-live-1 Is Full-Duplex Audio(2 posts)→
More from Models
- NCM: new text generation paradigm up to 31x faster than diffusion LMs with better quality — simonguozirui · 2026-10-15
- Gemma 4 26B priced at $0.07/M input tokens, ~40% below comparable providers — testingcatalog · 2026-10-15
- Epoch AI: GPT-6 Astra tops frontier models in Slay the Spire 2 but still loses to top humans — sandersted · 2026-10-15
- Google execs cite early signs of recursive self-improvement behind 3-4 week Gemini cadence — danielrock · 2026-10-15
- Claude systematically debunks the speculative EDAR-selenium hypothesis about East Asians — teortaxesTex · 2026-10-15
- Meta's Muse Wonder (Max) lands at #12 in Agent Arena at 2.1x the cost of its predecessor — arena · 2026-10-15