A MCP server for CosyVoice TTS using DashScope API
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"cosyvoice-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# cosyvoice-mcp A Python-based MCP server for integrating CosyVoice TTS with the Bailian platform. ## Installation ```bash pip install cosyvoice-mcp ``` ## Usage ```bash DASHSCOPE_API_KEY=sk-xxx cosyvoice-mcp ``` ## Features Supports JSON-RPC over HTTP (streamable-http) Compatible with FastMCP and DashScope TTS Base64-encoded audio output ## Request ### stdio tool: text_to_speech 说明：调用百炼平台CosyVoice V2进行语音合成 ### streamable-http - url: http://localhost:8000/mcp/tools/text_to_speech - method: POST ## Parameters - text: text string to be synthesized - voice_type: Such as the enumeration value of longxiaocheng_v2. Please refer to https://help.aliyun.com/zh/model-studio/cosyvoice-python-api?spm=a2c4g.11186623.0.i2#fbe0209896w38 ## 返回 ```json { "request_id": "7f6da1729d7345babb976d497f8bfaaa", "output": { "audio": { "data": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Lj...", //base64 encoded audio "mime_type": "audio/mpeg", "file_name": "哈哈_longxiaocheng_v2.mp3" }, "metrics": { "first_byte_latency": 738.578125, "text_length": 2 } } } ```
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.