Multimodal

Connects Claude to OpenAI, xAI, Gemini, ElevenLabs, and BFL APIs for generating and editing images, videos, audio, and transcriptions through a single interface. Exposes tools like generate_image, generate_video, generate_audio, and transcribe_audio with automatic provider selection based on which API keys you've configured. You can explicitly choose a provider per request or let it auto-select from what's available. All generated media saves to disk with descriptive filenames. Reach for this when you want Claude to generate visual or audio content without writing provider-specific code for each API, or when you're working across multiple media generation services and want consistent tool parameters.