Enables AI agents to synthesize natural speech using either platform system voices or premium OpenAI TTS, with automatic engine selection and graceful fallback.
Enables text-to-speech synthesis through a streaming, GPU-accelerated gateway, exposing a single tool that returns playable WAV audio with configurable voice and speed.
Enables AI agents to generate and play high-quality text-to-speech audio using the Kokoro model, with support for multiple voices, adjustable speaking speed, and audio caching.