Expand description
Multimodal tools: image generation + text-to-speech (§15).
Both target OpenAI-compatible endpoints so any provider that exposes
/images/generations or /audio/speech works. The user supplies the key
(env var, resolved at call time). No fake success: a missing key or a
non-2xx response returns a real error.
Structs§
- Image
Gen - Generate an image from a prompt via an OpenAI-compatible images endpoint.
- Transcribe
- Tts