Our most capable and efficient frontier model for professional work
Our most capable and efficient frontier model for professional work
Latest
Our smartest and most capable models to date with full tool access
Our smartest and most capable models to date with full tool access
A state-of-the-art model that makes precise, immediately usable visuals
A state-of-the-art model that makes precise, immediately usable visuals
Physically accurate, realistic, and controllable with synchronized dialogue and sound effects
Physically accurate, realistic, and controllable with synchronized dialogue and sound effects
A natively multimodal model capable of precise, accurate, photorealistic outputs
A natively multimodal model capable of precise, accurate, photorealistic outputs
Introducing next-generation audio models in the API
Introducing next-generation audio models in the API
Navigating the challenges and opportunities of synthetic voices
Navigating the challenges and opportunities of synthetic voices
Approaching human-level robustness and accuracy on English speech recognition
Approaching human-level robustness and accuracy on English speech recognition