GPT-Live
GPT-Live is a family of full-duplex voice models developed by OpenAI for continuous spoken interaction.
OpenAI
Explore OpenAI through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Speech & Audio AI
Articles that also belong to these categories. Counts cover all of OpenAI.
All articles (178)ChatGPT (48)Large Language Models (35)AI Models (29)Developer Tools (20)AI Agents (19)AI Tools & Products (17)Generative AI (13)People (13)Reasoning Models (12)AI Companies (9)Enterprise AI (9)Image Generation (9)AI Infrastructure (8)AI Safety (7)Natural Language Processing (7)AI Benchmarks (6)AI Incidents & Controversies (6)Reinforcement Learning (6)Speech & Audio AI (6)Voice AI (6)AI Policy & Regulation (5)AI Research (5)Artificial Intelligence (5)Open Source AI (5)AI Alignment (4)AI History (4)Diffusion Models (4)Multimodal AI (4)AI Hardware (3)Deep Learning (3)Healthcare AI (3)Software Development (3)Video Generation (3)AI Code Generation (2)AI for Science (2)AI in Gaming (2)Conversational AI (2)Data Centers (2)Information Retrieval (2)Music & Audio Generation (2)Small Language Models (2)Anthropic (1)Data Science (1)Education AI (1)Interpretability (1)Mathematics (1)Mixture of Experts (1)Programming Languages (1)Prompt Engineering (1)Robotics (1)Training & Optimization (1)
Showing 1-6 of 6 articles
GPT-Realtime / OpenAI Realtime API
GPT-Realtime is a family of speech-to-speech models exposed through the OpenAI Realtime API, a low-latency interface that lets developers build voice agents which take spoken audio in and return spoken audio…
GPT-Transcribe
GPT-Transcribe (gpt-transcribe) and GPT-Live-Transcribe (gpt-live-transcribe) are two closed-weight speech-to-text models that OpenAI added to its API on July 28, 2026.
OpenAI Realtime API
The OpenAI Realtime API is a speech-to-speech interface from OpenAI that lets developers build low-latency, bidirectional voice AI applications powered by GPT-4o and later by the purpose-built gpt-realtime…
Voice Engine (OpenAI)
Voice Engine is a speech-generation and voice-cloning model developed by OpenAI that can produce natural-sounding speech resembling a specific person from a single audio sample as short as 15 seconds.
Whisper
Whisper is an open-source family of automatic speech recognition (ASR) models developed by OpenAI and first released on September 21, 2022.