§ feed · storyline
Add voice to your agent
OpenAI's Agents SDK adds an experimental real-time voice pipeline via WebSockets, enabling continuous speech-to-text and text-to-speech in roughly 30 lines of server-side code.
An experimental voice pipeline for the Agents SDK enables real-time voice interactions over WebSockets.
Developers can now build agents with continuous STT and TTS in just ~30 lines of server-side code.
§ sources1 publication · timeline below
- blog.cloudflare.comAdd voice to your agentprimary