shield_lock
JinDaGe
← Back to MCP directory
publicPublicdnsLocal runtime

FlowSpeech MCP Server

FlowSpeech 的开源 MCP 服务器，通过 stdio 将上下文感知文本转语音接入 Claude Desktop、Cursor 等 MCP 客户端。支持情绪提示、停顿控制、30 多种声音、双人对话合成和声音列表查询，生成的音频保存到本地。无需在配置中填写 API Key。

article

README

FlowSpeech MCP Server\n\nFlowSpeech MCP Server 将上下文感知文本转语音能力接入支持 Model Context Protocol 的客户端。它通过本地 stdio 运行，可用 npx 直接启动，不需要在配置中写入 API Key。\n\n## 安装与配置\n\n要求 Node.js 18 或更高版本。在 Claude Desktop、Cursor 等 MCP 客户端中加入：\n\njson\n{\n "mcpServers": {\n "flowspeech": {\n "command": "npx",\n "args": ["-y", "mcp-flowspeech-server"],\n "env": {\n "FLOWSPEECH_OUTPUT_DIR": "~/flowspeech-audio"\n }\n }\n }\n}\n\n\n重启客户端后即可使用。FLOWSPEECH_OUTPUT_DIR 仅用于指定生成音频的本地保存目录，可省略。\n\n## 工具\n\n- flowspeech_tts：单声音文本转语音，支持情绪舞台指令和自定义输出路径。\n- flowspeech_tts_multi：将带有 Speaker1 / Speaker2 标记的双人对话合成为音频。\n- flowspeech_list_voices：列出 30 多种可用声音，并可按性别筛选。\n\n## 示例\n\n输入：***(say cheerfully: Good morning!)*** Today we are exploring AI voices.\n\n也可生成双人对话：\n\ntext\nSpeaker1: 欢迎收听。\nSpeaker2: 今天我们来讨论 AI 语音。\n\n\n源码：https://github.com/waeckerlinfederowicz66-sketch/mcp-flowspeech-server\n主页：https://flowspeech.io/\n许可证：MIT

READY-TO-PASTE CONFIG

MCP client config generator

Choose your client, fill the required environment variables, then copy a config generated from this server's published metadata

terminal
Environment variableslockValues stay in this browser tab and are not uploaded or saved
Claude Desktop
{
  "mcpServers": {
    "flowspeech": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-flowspeech-server"
      ],
      "env": {
        "FLOWSPEECH_OUTPUT_DIR": "~/.flowspeech-mcp/audio"
      }
    }
  }
}
Save toclaude_desktop_config.json
help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client