Whisper
Enables advanced audio transcription, text-to-speech generation, and audio processing using OpenAI's Whisper and GPT-4o models with support for multiple audio formats, file management, and parallel processing.
What is Whisper?
Whisper is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables advanced audio transcription, text-to-speech generation, and audio processing using openai's whisper and gpt-4o models with support for multiple audio formats, file management, and parallel pr...
Enables advanced audio transcription, text-to-speech generation, and audio processing using OpenAI's Whisper and GPT-4o models with support for multiple audio formats, file management, and parallel processing.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables advanced audio transcription, text-to-speech generat
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-whisperConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Whisper
MCP Server Whisper is a Model Context Protocol server that exposes OpenAI's Whisper and GPT-4o audio models as AI-assistant tools for transcription, enhanced transcription, interactive audio chat, and text-to-speech generation. It supports all OpenAI audio formats (mp3, mp4, wav, webm, flac, ogg, m4a), automatic file compression for files over 25 MB, parallel tool calls, and multiple voice and speed options for TTS. Developers, content creators, and researchers use it to give Claude or other AI clients a full audio processing pipeline from a single, standardized interface.
Prerequisites
- Python 3.10+ with uv installed
- An OpenAI API key with access to Whisper and GPT-4o audio models
- A directory of audio files accessible from the server's filesystem
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the mcp-server-whisper repository and change into the project directory.
git clone https://github.com/arcaputo3/mcp-server-whisper.git
cd mcp-server-whisperInstall dependencies with uv
Use uv to sync the project dependencies from the lock file.
uv syncCreate the .env file
Copy the provided example and fill in your OpenAI API key and the path to your audio files directory.
cp .env.example .env
# Edit .env:
# OPENAI_API_KEY=sk-...
# AUDIO_FILES_PATH=/path/to/your/audio/filesLaunch Claude with environment variables loaded
The included .mcp.json config is designed for local development. Use dotenv-cli to load the .env file and launch Claude with the MCP server active.
bunx dotenv-cli -- claudeAdd to Claude Desktop config for permanent setup
For Claude Desktop, add the server block to claude_desktop_config.json, supplying the env variables directly.
{
"mcpServers": {
"whisper": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-server-whisper",
"run",
"mcp-server-whisper"
],
"env": {
"OPENAI_API_KEY": "sk-your_openai_api_key",
"AUDIO_FILES_PATH": "/path/to/your/audio/files"
}
}
}
}Whisper Examples
Client configuration
Claude Desktop config to run mcp-server-whisper with uv, passing the OpenAI key and audio directory path as environment variables.
{
"mcpServers": {
"whisper": {
"command": "uv",
"args": [
"--directory",
"/home/user/mcp-server-whisper",
"run",
"mcp-server-whisper"
],
"env": {
"OPENAI_API_KEY": "sk-your_openai_api_key",
"AUDIO_FILES_PATH": "/home/user/audio"
}
}
}
}Prompts to try
Sample prompts that exercise the transcription, chat, and TTS tools.
- "Transcribe my latest audio file with detailed insights including tone and emotion."
- "List all MP3 files in my audio directory that are longer than 5 minutes."
- "Transcribe interview_2025.wav using the gpt-4o-transcribe model with word-level timestamps."
- "Chat with the audio file meeting.mp3 and summarize the key action items discussed."
- "Generate a text-to-speech audio file from this text using the 'alloy' voice at 1.2x speed: 'Welcome to our quarterly review.'"
- "Transcribe all files with 'podcast' in the filename and create professional transcripts for each."Troubleshooting Whisper
Transcription fails with 'File too large' error
Files over 25 MB are automatically compressed by the compress_audio tool before transcription. If the error persists, call compress_audio explicitly on the file first, then transcribe the compressed output.
OPENAI_API_KEY not found at runtime
Environment variables must be present when Claude Desktop spawns the server process. Set them in the 'env' block of the MCP config, not only in your shell profile. Verify with: echo $OPENAI_API_KEY in your shell.
Audio chat tool returns 'Model not supported' for gpt-4o-mini-audio-preview
The README notes that gpt-4o-mini-audio-preview has limitations with audio chat and is not recommended. Use gpt-4o-audio-preview (the default) instead for the chat_with_audio tool.
Frequently Asked Questions about Whisper
What is Whisper?
Whisper is a Model Context Protocol (MCP) server that enables advanced audio transcription, text-to-speech generation, and audio processing using openai's whisper and gpt-4o models with support for multiple audio formats, file management, and parallel processing. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Whisper?
Follow the installation instructions on the Whisper GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Whisper?
Whisper works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Whisper free to use?
Yes, Whisper is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Whisper Alternatives — Similar Communication Servers
Looking for alternatives to Whisper? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up 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 Whisper?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.