Skip to main content
Glama
speech-mcp-server

speech-mcp-server

Speech Model Context Protocol Server

An MCP server implementation for speech of volcengine

Features

Tools

  • asr Automatic Speech Recognition: Converts audio to text.

    • Args:

      • content: url or absolute path of the audio file to transcribe.

    • Returns:

      • Asr text

  • tts Text-to-Speech: Synthesizes text into audio.

    • Args:

      • text: The text to synthesize into speech.

      • speed: Speech speed (e.g., 1.0 for normal). default: 1.0.

      • encoding: Desired audio output format (e.g., 'mp3', 'wav'). default: 'mp3'.

    • Returns:

      • Return the path of audio file.

Related MCP server: whisper-transcribe-mcp

Configuration

The server requires the following environment variables to be set:

  • VOLC_APPID: Required, The APP ID for the VolcEngine.

  • VOLC_TOKEN: Required, The Access Token for the VolcEngine.

  • VOLC_VOICE_TYPE: Optional, Large speech synthesis model service voice_type, default is 'zh_female_meilinvyou_moon_bigtts'

  • VOLC_CLUSTER: Required, Large speech synthesis model service cluster ID

The services that need to be activated on Volcengine are: Large speech synthesis model、Streaming speech recognition large model、Large model for audio file recognition

You can set these environment variables in your shell.

MCP Settings Configuration

To add this server to your MCP configuration, add the following to your MCP settings file:

{
  "mcpServers": {
    "speech-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/FOLDER/src/mcp_server_speech",
        "run",
        "main.py"
      ]
    }
  }
}

or

{
    "mcpServers": {
        "speech-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/thundersoft-td/mcp-server-speech",
                "mcp-server-speech"
            ],
            "env": {
                "VOLC_APPID": "your appid",
                "VOLC_TOKEN": "your token",
                "VOLC_VOICE_TYPE": "tts voice type",
                "VOLC_CLUSTER": "tts cluster id",
            }
        }
    }
}

Usage

Running the Server

# Run the server with stdio transport (default)
python -m mcp_server_speech [--transport/-t {sse,stdio}]

License

This library is licensed under the MIT-0 License. See the LICENSE file.

Available Tools

2 tools
asrB
Automatic Speech Recognition: Converts audio to text.

Inputs: content (required).

ttsA
Text-to-Speech: Synthesizes text into audio.
Return the path of audio file.

Inputs: text (required), speed, encoding.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools, tts and asr, have completely distinct purposes: one synthesizes speech from text, the other converts audio to text. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    Both tool names are lowercase three-letter acronyms (tts, asr), following a consistent and predictable pattern. The naming style is uniform across the set.

    Tool Count3/5

    With only 2 tools, this is on the thin side. However, the two tools cover the essential capabilities of a speech server (synthesis and recognition), making the count borderline appropriate.

    Completeness4/5

    The tool set covers the two core directions of speech processing (text-to-speech and automatic speech recognition), representing solid coverage. Minor gaps such as voice selection or streaming are not included, but the fundamental workflows are fully supported.

    Related MCP Connectors

    Related MCP Servers