The Captions MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Captions account. It provides structured and secure access to Mirage video, speech, and caption tools, so your agent can generate speech, create videos, add styled captions, track progress, and download completed videos on your behalf.
- Speech generation: Have your agent turn written scripts into WAV speech using a known Mirage voice.
- Portrait video creation: Direct your agent to animate a portrait image with speech audio and create a video.
- Styled video captions: Let the agent browse available caption styles, review a chosen style, and add it to a video.
- Job tracking: Instruct your agent to check video generation and captioning progress, including any errors that need attention.
- Video library and downloads: Have your agent list your video jobs and download completed videos as MP4 files.