modelsAug 28
Introducing gpt-realtime and Realtime API updates
OpenAI released gpt-realtime, an advanced speech-to-speech model, and updated its Realtime API with new features like MCP server support, image input, and SIP phone calling. The updates enable more seamless interactions and broader application integration. You can now build applications that handle real-time speech and image inputs. These capabilities expand the potential for voice and multimodal interfaces.
Key takeaways
- gpt-realtime supports speech-to-speech interactions.
- Realtime API now includes MCP server support and image input.
- SIP phone calling support added for voice applications.