Skip to main content
Glama
deenesjakoruzh
ShreyasTembhare

MCP Audio Transcriber

by ShreyasTembhare
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

MCP 音频转录器

一个 Dockerized Python 工具，通过 AssemblyAI 的 API 实现模型上下文协议 (MCP)。上传或指向音频文件，即可接收结构化的 JSON 转录。

特征

  • AssemblyMCP ：使用 AssemblyAI 的 REST API 的具体 MCP 实现

  • 命令行界面（ app.py ）：

    python app.py <input_audio> <output_json>

  • Streamlit 网页用户界面( streamlit_app.py )：

    • 上传本地文件或粘贴 URL

    • 点击转录

    • 预览成绩单并下载 JSON

  • Docker 对环境一致性和可移植性的支持

Related MCP server: Fast-Whisper-MCP-Server

先决条件

  • Python 3.10+

  • AssemblyAI API 密钥

  • ffmpeg（用于本地解码，如果使用本地文件）

  • （可选）Docker 桌面/引擎

  • （可选）Streamlit（ pip install streamlit ）

🔧 安装

  1. 克隆 repo

    git clone https://github.com/ShreyasTembhare/MCP---Audio-Transcriber.git
cd MCP---Audio-Transcriber

  2. 创建.env

    ASSEMBLYAI_API_KEY=your_assemblyai_api_key_here

  3. 确保.gitignore包含：

    .env

  4. 安装 Python 依赖项

    pip install --upgrade pip
pip install -r requirements.txt

  5. 安装 ffmpeg

    • Ubuntu/Debian： sudo apt update && sudo apt install ffmpeg -y

    • Windows：从https://ffmpeg.org下载并将其bin/添加到您的 PATH

用法

1. CLI 转录

python app.py <input_audio> <output_json>

  • <input_audio> ：AssemblyAI 支持的任何文件或 URL

  • <output_json> ：生成的 JSON 的路径

例子：

python app.py data/input.ogg data/output.json
cat data/output.json

2. Streamlit Web UI

streamlit run streamlit_app.py

3. Docker

构建图像：

docker build -t mcp-transcriber .

运行它（挂载你的数据/文件夹）：

docker run --rm \
  -e ASSEMBLYAI_API_KEY="$ASSEMBLYAI_API_KEY" \
  -v "$(pwd)/data:/data" \
  mcp-transcriber:latest \
  /data/input.ogg /data/output.json

然后检查：

ls data/output.json
cat data/output.json

Windows PowerShell：

docker run --rm `
  -e ASSEMBLYAI_API_KEY=$env:ASSEMBLYAI_API_KEY `
  -v "${PWD}\data:/data" `
  mcp-transcriber:latest `
  /data/input.ogg /data/output.json

项目结构

MCP-Audio-Transcriber/
├── app.py               # CLI entrypoint (AssemblyMCP only)
├── mcp.py               # ModelContextProtocol + AssemblyMCP
├── streamlit_app.py     # Streamlit interface
├── requirements.txt     # assemblyai, python-dotenv, streamlit, etc.
├── Dockerfile           # builds the container
├── .gitignore           # ignores .env, __pycache__, etc.
├── LICENSE              # MIT license
└── data/                # sample input and output
    ├── input.ogg
    └── output.json

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Fast-Whisper-MCP-Server

    BigUncle
    F
    license
    Not graded
    quality
    D
    maintenance
    A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities with support for multiple model sizes, batch processing, and various output formats.
    17
    -

  • MCP Audio Server

    thrid3v
    F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol (MCP) server that gives AI agents the ability to process audio files — transcribe speech to text, detect spoken languages, and extract audio metadata.
    1
    -

  • Whisper MCP Server

    jwulff
    A
    license
    A
    quality
    F
    maintenance
    Provides local audio transcription using whisper.cpp, supporting multiple models and audio formats. Enables transcription of audio files via MCP tools with optional timestamps.
    3
    122 npm
    3
    MIT