Reference materials for non-real-time speech synthesis, speech recognition, audio generation, and audio/video translation API.
This directory provides API references for non-real-time audio calls. Non-real-time calls can still use streaming output according to the specific API. For voice cloning and voice design APIs, please refer uniformly to Voice Customization.
For API references on real-time multimodal interactions, real-time speech recognition, real-time speech synthesis, real-time speech dialogue, and real-time audio/video translation, see Realtime API Overview.