multimodal for Gemini CLI
io.github.rsmdt/multimodal
Multi-provider media generation — images, video, audio, and transcription via a unified interface
client:Gemini CLI
transport:stdio
runtime:npm
Install multimodal in Gemini CLI
~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json
{
"mcpServers": {
"multimodal": {
"command": "npx",
"args": [
"-y",
"@r16t/multimodal-mcp"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"XAI_API_KEY": "<XAI_API_KEY>",
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>",
"BFL_API_KEY": "<BFL_API_KEY>",
"MEDIA_OUTPUT_DIR": "<MEDIA_OUTPUT_DIR>"
}
}
}
}
Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs