Skip to main content
Glama

whisper-mcp

本地 Whisper 转录能力,以 MCP 服务器的形式对外暴露——因此任何 MCP 客户端(Claude Desktop、Claude Code 等)都可以直接以工具调用的形式转录音频/视频文件、生成 .srt 字幕,并将字幕烧录到视频中。无需云 API,也无需手动“运行脚本然后再去读取输出文件”这一步。

基于 faster-whisper 进行推理,并使用 ffmpeg 进行音频提取 / 字幕烧录。

Claude Code 调用 transcribe 工具并返回带时间戳的转录文本

架构

MCP client (Claude, etc.) --stdio--> whisper-mcp server --> faster-whisper (Whisper model)
                                                        \--> ffmpeg (audio extract / burn-in)

服务器会在进程的整个生命周期内,将已加载的 Whisper 模型缓存在内存中,因此同一会话中重复的工具调用无需再次承担模型加载时间。

Related MCP server: Whisper MCP Server

工具

工具

描述

transcribe(path, model_size="small", device="auto")

以结构化数据的形式返回检测到的语言与带时间戳的片段。

generate_srt(path, output_path=None, model_size="small", device="auto")

转录并写入一个 .srt 文件。

burn_captions(video_path, srt_path, output_path=None)

通过 ffmpeg.srt 字幕烧录到视频中。

要求

  • Python 3.10+

  • PATH 中包含 ffmpeg

  • 可选:支持 CUDA 的 GPU(自动回退到 CPU)

安装与运行

pip install -e ".[dev]"
whisper-mcp

或者,零安装:

uvx --from git+https://github.com/Chain-P/whisper-mcp whisper-mcp

在 MCP 客户端中配置

添加到你的客户端 MCP 配置中(例如 Claude Code 的 .mcp.json,或 Claude Desktop 的 claude_desktop_config.json):

{
  "mcpServers": {
    "whisper": {
      "command": "whisper-mcp"
    }
  }
}

然后让客户端转录一个文件,例如:“转录 samples/podcast_clip.mp4 并给我 SRT 文件。”

开发

pip install -e ".[dev]"
ruff check .
pytest                        # unit tests only
pytest -m integration         # + real transcription against a sample file

路线图

  • 说话人分离(pyannote.audio / whisperx),用于在 SRT 输出中对多个说话人进行标注。

  • 针对长时间转录的 MCP 进度通知。

  • 一个 resource,用于暴露最近的转录历史。

许可证

MIT

Install Server
A
license - permissive license
A
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    Enables high-quality transcription and subtitle generation from local media files or URLs using Faster Whisper on local hardware. It supports automatic language detection and integration with MCP clients for seamless speech-to-text workflows.
    3
  • 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
    67
    3
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Enables local media processing (video/audio) using FFmpeg and FFprobe, allowing frame extraction, audio conversion, and metadata retrieval through natural language.
    5
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.
    PolyForm Noncommercial 1.0.0

View all related MCP servers

Related MCP Connectors

  • OCR, transcription, file extraction, and image generation for AI agents via MCP.

  • Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.

  • MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Chain-P/whisper-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server