| Mobile Web

OpenAI applies new voice model to ChatGPT Voice

OpenAI said on Thursday it has improved ChatGPT Voice by applying a new speech model, GPT-Live, that understands conversational context in real time. The company said the update reduces cut-offs and response delays and enhances real-time interpretation. GPT-Live continuously processes audio, allowing the system to react mid-speech and handle resumed questions. OpenAI also plans to expand the architecture across backend models, input-output methods and API use cases.