Fast Whisper
A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.
What is Fast Whisper?
Fast Whisper is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to high-performance speech recognition mcp server based on faster whisper, providing efficient audio transcription capabilities.
A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A high-performance speech recognition MCP server based on Fa
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx fast-whisper-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Fast Whisper
Fast Whisper MCP Server is a locally-run speech recognition server that wraps the Faster Whisper library and exposes it as an MCP tool, enabling AI assistants to transcribe audio files directly from disk without sending audio to any external API. It supports all Whisper model sizes from tiny to large-v3 and automatically uses CUDA GPU acceleration when available, making it significantly faster than the original OpenAI Whisper implementation. Developers use it to add offline, private transcription capabilities to Claude and other MCP clients, generating SRT, VTT, or JSON transcript outputs from single files or entire folders.
Prerequisites
- Python 3.8 or later installed on the host machine
- pip for installing Python dependencies (requirements.txt provided in the repo)
- Optional: an NVIDIA GPU with CUDA 12.6 drivers for hardware-accelerated transcription
- Claude Desktop or another MCP-compatible client
- Git to clone the repository
Clone the repository
Clone the Fast Whisper MCP Server repository to your local machine and enter the project directory.
git clone https://github.com/BigUncle/Fast-Whisper-MCP-Server.git
cd Fast-Whisper-MCP-ServerInstall Python dependencies
Install the required packages from the provided requirements file. If you have an NVIDIA GPU, also install the CUDA-enabled PyTorch build to unlock hardware acceleration.
pip install -r requirements.txt
# Optional: CUDA 12.6 GPU acceleration
pip install torch==2.6.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu126Test the server standalone
Start the server directly or use the MCP dev tool to verify it launches without errors before connecting it to a client.
python whisper_server.py
# Or use MCP inspector:
mcp dev whisper_server.pyConfigure Claude Desktop
Open claude_desktop_config.json and add the server entry below. Update the path to the absolute location of whisper_server.py on your machine.
{
"mcpServers": {
"whisper": {
"command": "python",
"args": ["/absolute/path/to/Fast-Whisper-MCP-Server/whisper_server.py"]
}
}
}Restart Claude Desktop and transcribe audio
After restarting the client, ask Claude to transcribe an audio file by providing the absolute file path. The server exposes three tools: get_model_info, transcribe, and batch_transcribe.
Fast Whisper Examples
Client configuration (Claude Desktop)
Full claude_desktop_config.json entry for the Fast Whisper MCP Server. Update the path to match your local clone location.
{
"mcpServers": {
"whisper": {
"command": "python",
"args": ["/Users/yourname/Fast-Whisper-MCP-Server/whisper_server.py"]
}
}
}Prompts to try
Example prompts that exercise the three tools exposed by the Fast Whisper MCP Server.
- "What Whisper models are available and which one is currently loaded?"
- "Transcribe the audio file at /Users/me/recordings/meeting.mp3 and return SRT subtitles."
- "Batch transcribe all .wav files in /Users/me/podcasts/ and save the results as JSON."
- "Transcribe /tmp/interview.m4a using the large-v3 model for best accuracy."Troubleshooting Fast Whisper
Server fails to start with a 'faster-whisper not found' import error
Run pip install -r requirements.txt again inside the project directory, ensuring you are using the same Python environment that Claude Desktop will invoke. Check with 'which python' and 'python --version'.
Transcription is very slow even on modern hardware
Without a compatible GPU, Faster Whisper runs on CPU which is slower. Install the CUDA PyTorch build if you have an NVIDIA GPU, or switch to a smaller model size (tiny or base) by modifying the model_size parameter in whisper_server.py.
Claude Desktop cannot find the server after configuration
The args path must be an absolute path, not a relative one. On macOS, use the full path starting with /Users/. On Windows, use backslashes or forward slashes, e.g. C:/Users/name/project/whisper_server.py.
Frequently Asked Questions about Fast Whisper
What is Fast Whisper?
Fast Whisper is a Model Context Protocol (MCP) server that high-performance speech recognition mcp server based on faster whisper, providing efficient audio transcription capabilities. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Fast Whisper?
Follow the installation instructions on the Fast Whisper GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Fast Whisper?
Fast Whisper works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Fast Whisper free to use?
Yes, Fast Whisper is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Fast Whisper Alternatives — Similar Developer Tools Servers
Looking for alternatives to Fast Whisper? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Fast Whisper in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Fast Whisper?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.