{"$schema":"https://schemas.agentskills.io/discovery/0.2.0/schema.json","skills":[{"name":"fish-audio-api","type":"skill-md","description":"Write direct HTTP / WebSocket calls to the Fish Audio platform (TTS, ASR, voice models, wallet, real-time TTS streaming) without depending on the Python or JavaScript SDK. Use when the user asks to call Fish Audio from curl, a language without an official SDK, an edge/runtime environment that cannot install the SDK, or when they explicitly want raw REST / WebSocket code. Covers authentication, endpoint URLs, required headers, request / response schemas, MessagePack vs JSON vs multipart encoding rules, multi-speaker dialogue, and the WebSocket streaming protocol.","url":"/.well-known/agent-skills/fish-audio-api/skill.md","digest":"sha256:d55b0fdec32bf95c43c9b72fb63a64d302e94e451866a3574d1c0ddd5ad44dc1"}]}