A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add whisper-speech-recognition -- python whisper_server.py~/.codex/config.toml
[mcp_servers.whisper-speech-recognition]
command = "python"
args = ["whisper_server.py"]
# codex mcp add whisper-speech-recognition -- python whisper_server.py~/.cursor/mcp.json
{
"mcpServers": {
"whisper-speech-recognition": {
"command": "python",
"args": [
"whisper_server.py"
]
}
}
}.vscode/mcp.json
{
"servers": {
"whisper-speech-recognition": {
"type": "stdio",
"command": "python",
"args": [
"whisper_server.py"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"whisper-speech-recognition": {
"command": "python",
"args": [
"whisper_server.py"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"whisper-speech-recognition": {
"command": "python",
"args": [
"whisper_server.py"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"whisper-speech-recognition": {
"command": "python",
"args": [
"whisper_server.py"
]
}
}
}