mcp-flowspeech-server/SKILL.md

name, description

name	description
flowspeech-tts	Use FlowSpeech to convert text, narration scripts, and two-speaker dialogue into human-like speech with emotion control, pause control, and 30+ voices through the FlowSpeech MCP server.

FlowSpeech TTS

Use this skill when a user wants to create audio from text with FlowSpeech, including narration, educational audio, product demos, creator scripts, short voiceovers, or two-speaker dialogue.

FlowSpeech is a context-aware text-to-speech tool for human-like audio with emotion control, pause control, and 30+ voices. Learn more at https://flowspeech.io/.

When To Use

• The user asks for text-to-speech, AI voice, narration, voiceover, spoken audio, or dialogue audio.
• The user wants expressive delivery with emotion stage directions.
• The user needs a local audio file generated from plain text or a two-speaker script.
• The user wants to explore available FlowSpeech voices before generating audio.

Setup

Install or run the FlowSpeech MCP server:

npx -y mcp-flowspeech-server

For MCP clients, configure the server with stdio transport:

{
  "mcpServers": {
    "flowspeech": {
      "command": "npx",
      "args": ["-y", "mcp-flowspeech-server"],
      "env": {
        "FLOWSPEECH_OUTPUT_DIR": "~/flowspeech-audio"
      }
    }
  }
}

Do not ask the user to paste secrets, account credentials, or private tokens into chat. If the user needs custom credentials for a private deployment, tell them to store those values in their local MCP client environment or secret manager.

Workflow

1. Clarify the target format: single voice, two-speaker dialogue, or voice exploration.
2. If the user has not chosen a voice, use flowspeech_list_voices or pick a sensible default.
3. For single-speaker audio, call flowspeech_tts with the text and selected voice.
4. For two-speaker audio, call flowspeech_tts_multi with Speaker1: and Speaker2: labels.
5. Return the generated audio file path and briefly describe the voice choices used.

Emotion And Pause Control

FlowSpeech supports inline emotion cues with stage directions:

***(say cheerfully: Welcome back!)***
Today we are walking through the new release.
***(say thoughtfully: This part matters.)***

Use emotion cues sparingly. Keep them tied to the content instead of decorating every sentence.

Example Requests

• "Turn this lesson into a warm narration."
• "Create a two-host podcast intro from this script."
• "Read this product update in a calm professional voice."
• "List the available female voices before generating audio."

Output

The MCP server saves generated audio locally and returns the file path. If the user needs a different location, pass a custom output_path.