{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_d4hwa6p5x6qn","handle":"mcp-bytedance-tts","url":"https://wellknown.network/agents/mcp-bytedance-tts","links":{"self":"https://wellknown.network/agents/mcp-bytedance-tts/record.json","html":"https://wellknown.network/agents/mcp-bytedance-tts","markdown":"https://wellknown.network/agents/mcp-bytedance-tts/record.md","api":"https://wellknown.network/api/v1/agents/mcp-bytedance-tts","status":"https://wellknown.network/api/v1/agents/mcp-bytedance-tts/status","claim":"https://wellknown.network/agents/mcp-bytedance-tts/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-bytedance-tts/claim.json","badge":"https://wellknown.network/agents/mcp-bytedance-tts/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-bytedance-tts/history","tools":"https://wellknown.network/api/v1/agents/mcp-bytedance-tts/tools"},"ard":{"identifier":"urn:air::server:mcp-bytedance-tts","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-bytedance-tts","summary":"MCP server for text-to-speech using bytedance-tts - generates audio from text","description":"# MCP Bytedance TTS 语音生成器\n\n本项目是一个 [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) 服务器，基于字节跳动 OpenSpeech TTS 的 HTTP 接口，将文本转换为语音音频。\n遵循\"只使用 HTTP，不使用 WebSocket\"的约定。\n\n## ✨ 功能特性\n\n- 文本转语音：调用 Bytedance OpenSpeech TTS HTTP 接口生成音频\n- 音色管理：支持通过 voice-types.json 将可读名称映射到官方 voice_type\n- 简单集成：暴露 MCP 工具，Agent 直接调用生成 WAV 文件\n- 跨平台运行：Windows、Linux、macOS\n\n## 调用示例\n```txt\n使用\"京腔侃爷（多情感）\"的音色,创建如下内容的音频:\n\n林芝海关关长王存瑞介绍道，我们依托智慧海关“高原特色产品出口”场景链建设，落实“随报、随检、随放”便利举措，大幅压缩报检时间，让高原蜂蜜以最优品质、最快速度抵港，不仅能让香江的同胞品尝到独特的“高原风味”，也是助力农民致富、乡村振兴的“甜蜜事业”。\n```\n\n## 🚀 安装\n\n### 使用 uvx（推荐）\n\n```bash\nuvx mcp-bytedance-tts@latest  # 直接运行、更新，无需安装\n```\n\n或者使用 pipx 安装：\n\n```bash\npipx install mcp-bytedance-tts\n```\n\n### 使用 uvx 运行（推荐）\n\n```bash\nuvx mcp-bytedance-tts\n```\n\n### 构建和发布\n```bash\nrm -rf dist && pip install build && python -m build && pip install twine && twine upload dist/*\n```\n\n## ⚙️ 配置\n\n在 [config.json](src/main/config.json) 中填写以下字段：\n- appid：控制台获取的应用 ID\n- accessToken：控制台获取的访问令牌（用于 Authorization）\n- secretKey：控制台获取的密钥（当前 HTTP 方案不直接使用）\n- defaultVoiceType：默认的 voice_type（如 zh_male_xxx）\n- defaultAudioEncoding：音频编码（默认 wav）\n- uid：用户标识\n\n可选在项目 src/ 目录放置 voice-types.json，将“可读名称”映射到“官方 voice_type ID”。当调用时传入名称会自动解析为 ID。\n\n安全提示：请勿将密钥、令牌提交到版本库。\n\n## 🖥️ MCP 客户端配置\n\n在 MCP 客户端（例如 Claude Desktop、Cursor）的配置中添加：\n\n使用 uvx（推荐）\n```json\n{\n  \"mcpServers\": {\n    \"McpByteDanceTTS\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-bytedance-tts\"]\n    }\n  }\n}\n```\n\n## 🛠️ 可用工具\n\n### mcp_bytedance_tts_generate_audio\n\n使用字节跳动 OpenSpeech TTS 的 HTTP 接口（仅 HTTP）将文本生成音频文件。\n\n参数\n- text（string，必填）：要转换为语音的文本\n- voiceType（string，可选）：音色名称或 voice_type ID；未提供时使用 defaultVoiceType\n- outputDir（string，必填）：输出目录\n- useSSML（boolean，可选）：是否使用SSML格式，当值为true时在请求中添加text_type:ssml；未提供时默认为 false\n\n```json\n{\n  \"name\": \"mcp_bytedance_tts_generate_audio\",\n  \"arguments\": {\n    \"text\": \"请将这段文字合成为语音文件\",\n    \"voiceType\": \"zh_male_yuanboxiaoshu_moon_bigtts\",\n    \"outputDir\": \"./output\",\n    \"useSSML\": true\n  }\n}\n```\n\n返回值\n- 文本：生成成功消息，包含最终 WAV 文件路径（例如 ./output/1767514828_93829.wav）\n\n工具定义位置…","publisher":null,"homepage":"https://github.com/aardpro/mcp-bytedance-tts","repository":"https://github.com/aardpro/mcp-bytedance-tts","version":"1.0.13","license":null,"protocols":["mcp"],"tags":["audio","bytedance-tts","mcp","text-to-speech","tts"],"pricing":null,"endpoints":[{"url":"pypi:mcp-bytedance-tts","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"declared"}],"categories":["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":"mcp-bytedance-tts","registry":"pypi","observedAt":"2026-10-22T08:24:10.592Z","publishedAt":"2026-01-11T12:38:28.882746Z","latestVersion":"1.0.13"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-bytedance-tts","url":"https://pypi.org/project/mcp-bytedance-tts/","firstSeenAt":"2026-09-10T00:24:39.422Z","fetchedAt":"2026-10-22T08:22:20.079Z","normalizedAt":"2026-10-22T08:22:20.079Z"}]},"firstSeenAt":"2026-09-10T00:24:39.422Z","updatedAt":"2026-10-22T08:24:10.592Z"}