{"slug": "gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations", "title": "GPT-Live-1.1: Full-duplex voice model for multilingual conversations", "summary": "OpenAI released GPT-Live-1.1, a full-duplex voice model that can listen while it speaks, priced at $0.05 per minute for active live sessions and $0.02 per minute for standby WebRTC sessions where inference is paused. OpenAI said GPT-Live-1.1 transcribes speech more accurately than GPT-Live-1 and maintains a more consistent accent and voice across languages, with developers able to describe in plain language when the model should hand a task to a backend for reasoning or tool use. The model accepts and outputs audio and text, supports streaming and function calling but not structured outputs or fine-tuning, and carries separate concurrent-session limits from GPT-Live-1.", "body_md": "GPT-Live-1.1\n\n`gpt-live-1.1`\nFull-duplex voice model for multilingual conversations.\n\nPerformance\n\n—\n\nNot specified\n\nSpeed\n\n—\n\nNot specified\n\nPrice\n\n$0.05\n\nActive\n\nInput\n\nAudio, Text\n\nOutput\n\nAudio, Text\n\nGPT-Live-1.1 can listen while it speaks. Compared with GPT-Live-1, it transcribes speech more accurately and maintains a more consistent accent and voice across languages. Describe in plain language when the model should hand a task to your backend for reasoning or tool use.\n\nLearn how to [start a voice session](https://developers.openai.com/api/docs/guides/live), [prompt GPT-Live](https://developers.openai.com/api/docs/guides/live-prompting), and [configure delegation](https://developers.openai.com/api/docs/guides/live-delegation).\n\nPricing\n\nVoice sessions are billed by duration. Backend model and tool usage is billed separately. See the \n\n[pricing page](https://developers.openai.com/api/docs/pricing).\nLive session duration\n\nPer minute\n\nActive\n\n$0.05\n\nStandby\n\n$0.02\n\nThe lower standby rate applies to WebRTC sessions while inference is paused. See [GPT-Live pricing](https://developers.openai.com/api/docs/pricing#live-session-duration).\n\nModalities\n\nText\n\nInput and output\n\nImage\n\nNot supported\n\nAudio\n\nInput and output\n\nVideo\n\nNot supported\n\nEndpoints\n\nLive\n\nv1/live/sessions\n\nChat Completions\n\nv1/chat/completions\n\nResponses\n\nv1/responses\n\nRealtime\n\nv1/realtime\n\nRealtime translation\n\nv1/realtime/translations\n\nRealtime transcription\n\nv1/realtime/transcription_sessions\n\nAssistants\n\nv1/assistants\n\nBatch\n\nv1/batch\n\nFine-tuning\n\nv1/fine-tuning\n\nEmbeddings\n\nv1/embeddings\n\nImage generation\n\nv1/images/generations\n\nVideos\n\nv1/videos\n\nImage edit\n\nv1/images/edits\n\nSpeech generation\n\nv1/audio/speech\n\nTranscription\n\nv1/audio/transcriptions\n\nTranslation\n\nv1/audio/translations\n\nModeration\n\nv1/moderations\n\nCompletions (legacy)\n\nv1/completions\n\nFeatures\n\nStreaming\n\nSupported\n\nFunction calling\n\nSupported\n\nStructured outputs\n\nNot supported\n\nFine-tuning\n\nNot supported\n\nPredicted outputs\n\nNot supported\n\nSnapshots\n\nUse `gpt-live-1.1` in your API requests.\n\ngpt-live-1.1\n\nRate limits\n\nGPT-Live-1.1 and GPT-Live-1 have separate concurrent-session limits. Each model’s limit applies across inference regions.\n\nSee your [organization's limits](https://platform.openai.com/settings/organization/limits) for the rate limits that apply to your account.", "url": "https://wpnews.pro/news/gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations", "canonical_source": "https://developers.openai.com/api/docs/models/gpt-live-1.1", "published_at": "2026-11-19 20:06:15+00:00", "updated_at": "2026-11-19 20:15:35.665573+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "developer-tools", "natural-language-processing"], "entities": ["OpenAI", "GPT-Live-1.1", "GPT-Live-1", "WebRTC"], "also_reported_by": [], "takeaway": "GPT-Live-1.1 adds full-duplex listening-while-speaking with more accurate transcription and cross-language voice consistency, billed at $0.05 per active minute and $0.02 per standby minute, with delegation to backend reasoning or tools configured in plain language.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations", "markdown": "https://wpnews.pro/news/gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations.md", "text": "https://wpnews.pro/news/gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations.txt", "jsonld": "https://wpnews.pro/news/gpt-live-1-1-full-duplex-voice-model-for-multilingual-conversations.jsonld"}}