{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_6wagghvzpx3n","handle":"voicemcpserver","url":"https://wellknown.network/agents/voicemcpserver","links":{"self":"https://wellknown.network/agents/voicemcpserver/record.json","html":"https://wellknown.network/agents/voicemcpserver","markdown":"https://wellknown.network/agents/voicemcpserver/record.md","api":"https://wellknown.network/api/v1/agents/voicemcpserver","status":"https://wellknown.network/api/v1/agents/voicemcpserver/status","claim":"https://wellknown.network/agents/voicemcpserver/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/voicemcpserver/claim.json","badge":"https://wellknown.network/agents/voicemcpserver/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:voicemcpserver","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"voicemcpserver","summary":"MCP Server for Alibaba Cloud CosyVoice","description":"# CosyVoice MCP Server\n\nA Model Context Protocol (MCP) server for Alibaba Cloud's [CosyVoice](https://help.aliyun.com/zh/model-studio/cosyvoice-voice-list) text-to-speech service.\n\nThis server allows you to generate high-quality, expressive speech from text using Alibaba Cloud's state-of-the-art CosyVoice models (V2 and V3).\n\n## Features\n\n- **List Voices**: Retrieve a curated list of high-quality voices suitable for various scenarios (social, narration, customer service, etc.).\n- **Speech Synthesis**: Convert text to speech with support for:\n    - **Model Selection**: Choose between `cosyvoice-v2` (standard) and `cosyvoice-v3-flash` (emotional).\n    - **Control Parameters**: Adjust volume, speech rate, and pitch rate.\n    - **Emotion Control**: Use natural language instructions to control emotion (V3 models only).\n        - Supported emotions: `neutral`, `fearful`, `angry`, `sad`, `surprised`, `happy`, `disgusted`.\n        - Format: `\"你说话的情感是<emotion>。\"`\n    - **SSML Support**: Use SSML tags (e.g., `<break time=\"2s\"/>`) for precise pause control.\n    - **File Saving**: Save generated audio directly to a local file path.\n\n## Configuration\n\nYou need an Alibaba Cloud DashScope API Key. Set it as an environment variable:\n\n```bash\nexport COSYVOICE_MCP_DASHSCOPE_API_KEY=your_api_key_here\n```\n\n(Alternatively, `DASHSCOPE_API_KEY` is also supported).\n\n### Optional Configuration\n\n- `COSYVOICE_DEFAULT_OUTPUT_DIR`: Set a default directory for saving generated audio files if `output_file` is not specified.\n\n```bash\nexport COSYVOICE_DEFAULT_OUTPUT_DIR=~/Desktop/CosyVoiceOutput\n```\n\n## MCP Client Configuration\n\nAdd the following to your MCP client configuration (e.g., `claude_desktop_config.json`):\n\n### Using `uvx` (Recommended)\n\nYou can run the server directly from PyPI using `uvx`:\n\n```json\n{\n  \"mcpServers\": {\n    \"cosyvoice\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"voicemcpserver\"\n      ],\n      \"env\": {\n        \"COSYVOICE_MCP_DASHSCOPE_API_KEY\": \"your_api_key_here\"…","publisher":null,"homepage":null,"repository":null,"version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:voicemcpserver","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":0.917,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.802,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"voicemcpserver","registry":"pypi","observedAt":"2026-09-10T15:25:16.809Z","publishedAt":"2025-12-04T15:34:02.011495Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"voicemcpserver","url":"https://pypi.org/project/voicemcpserver/","firstSeenAt":"2026-09-10T15:23:51.754Z","fetchedAt":"2026-09-10T15:23:51.754Z","normalizedAt":"2026-09-10T15:23:51.754Z"}]},"firstSeenAt":"2026-09-10T15:23:51.754Z","updatedAt":"2026-09-10T15:25:16.809Z"}