MCP.so
登录

Transcription MCP Sever

@Charisma2595

关于 Transcription MCP Sever

暂无概览

基本信息

分类

其他

运行时

python

传输方式

stdio

发布者

Charisma2595

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "transcription_mcp_server": {
      "command": "uv",
      "args": [
        "run",
        "mcp",
        "dev",
        "mcpserver_transcription.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Transcription MCP Sever?

Transcription MCP Sever is an MCP (Model-Context-Protocol) server for transcribing MP3 audio files using the AssemblyAI API. It provides command-line and Docker-based tools to transcribe audio, targeting podcasters, content creators, educators, and business teams.

How to use Transcription MCP Sever?

Install dependencies from requirements.txt, set your AssemblyAI API key as the API_KEY environment variable, then run with mcp dev or mcp install to connect with an AI assistant like Claude, or use the provided client script with a file path.

Key features of Transcription MCP Sever

  • Transcribe MP3 audio files into JSON transcripts via AssemblyAI API
  • Speaker diarization (speaker labels) enabled
  • Saves transcripts in a local "transcripts/" directory
  • Accepts file paths via command-line interface (Google Fire)
  • Ready to run in a Docker container for portability

Use cases of Transcription MCP Sever

  • Transcribing podcast episodes for show notes and searchability
  • Converting educational lecture recordings into text transcripts
  • Generating meeting summaries for business teams
  • Creating searchable archives of audio content for content creators

FAQ from Transcription MCP Sever

What are the prerequisites?

Python 3.10+, Uvicorn, Google Fire, an AssemblyAI API key, and optionally Docker.

How do I set my AssemblyAI API key?

Set it as an environment variable: export API_KEY="your_assemblyai_api_key" on Linux/macOS, or set API_KEY="your_assemblyai_api_key" on Windows CMD.

Where are the transcripts saved?

All transcripts are saved in a local folder named transcripts/.

What audio formats are supported?

Only MP3 files are supported for transcription.

Can I run Transcription MCP Sever without Docker?

Yes, it can run directly on a local machine using Python and Uvicorn. Docker is optional.

评论

其他 分类下的更多 MCP 服务器