mini_whisper_mcp
Provides audio transcription capabilities using OpenAI Whisper models, supporting various model sizes and audio formats.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mini_whisper_mcptranscribe this audio file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mini-whisper-mcp
MCP server for audio transcription using OpenAI Whisper.
Requirements
Python 3.11+
ffmpeg(apt install ffmpeg/brew install ffmpeg)
Related MCP server: Whisper CLI MCP Server
Install
uv syncRun
stdio (for local agents)
uv run python -m mini_whisper_mcp --transport stdioHTTP
uv run python -m mini_whisper_mcp --transport streamable-http --host 0.0.0.0 --port 8000Docker
docker build -t mini-whisper-mcp .
docker run -p 8000:8000 mini-whisper-mcpDocker Compose
Create a docker-compose.yml alongside your calling agent:
services:
mini-whisper-mcp:
image: mini-whisper-mcp
build: ./mini-whisper-mcp # path to this repo
ports:
- "8000:8000"
environment:
MCP_TRANSPORT: streamable-http
MCP_HOST: 0.0.0.0
MCP_PORT: "8000"
restart: unless-stopped
your-agent:
build: ./your-agent
environment:
WHISPER_MCP_URL: http://mini-whisper-mcp:8000/mcp
depends_on:
- mini-whisper-mcpdocker compose upThe agent connects to the MCP server at http://mini-whisper-mcp:8000/mcp using the service name as hostname.
Configuration
Env var | Default | Description |
|
|
|
|
| Host for HTTP mode |
|
| Port for HTTP mode |
MCP Tools
health_check
Basic server health check. Returns "ok".
transcribe
Param | Type | Default | Description |
| string | — | Base64-encoded audio file content |
| string |
|
|
| string |
| File extension hint: |
Models are cached in memory after first load. Larger models are more accurate but slower.
Usage example (calling agent)
import base64
with open("audio.mp3", "rb") as f:
audio_b64 = base64.b64encode(f.read()).decode()
result = await mcp_client.call_tool("transcribe", {
"audio_b64": audio_b64,
"model": "base",
"suffix": ".mp3",
})Testing with MCP Inspector
npx @modelcontextprotocol/inspector uv run python -m mini_whisper_mcp --transport stdioFor HTTP, start the server first then connect Inspector to http://localhost:8000/mcp.
Claude Desktop config (stdio)
{
"mcpServers": {
"whisper": {
"command": "uv",
"args": ["--directory", "/path/to/mini-whisper-mcp", "run", "python", "-m", "mini_whisper_mcp", "--transport", "stdio"]
}
}
}Project structure
mini_whisper_mcp/
├── __main__.py # CLI entrypoint (--transport, --host, --port)
├── server.py # MCP tools
└── models.py # Whisper model loader with CUDA fallbackThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/rhuanca/mini_whisper_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server