Sora
OpenAIOpenAI's video model: text or image in, short clip out, with storyboard control.
Reads Loom recordings, titles, and transcripts for an account. The use case is turning a recorded walkthrough into written documentation, which is faster than re-watching it. The permission question is whose recordings the token…
Pulling transcripts and titles from screen recordings for documentation
Transcribing without consent — recordings often include other people
Reads Loom recordings, titles, and transcripts for an account. The use case is turning a recorded walkthrough into written documentation, which is faster than re-watching it. The permission question is whose recordings the token can access, because they usually include other people’s screens and voices.
npx -y loom-mcpPaste this into your MCP client config, then restart the client.
{
"mcpServers": {
"avbbc": {
"command": "npx",
"args": ["-y", "loom-mcp"]
}
}
}Reads Miro boards, frames, and sticky notes, and can create items. The natural job is post-workshop synthesis: turn a board of stickies into themes with counts. The …
Searches and reads Confluence pages and spaces through the API. The value is retrieval: the answer to a process question usually exists in a page nobody searches by …
Reads Zoom meeting metadata, recordings available to the account, and transcripts where the plan includes them. The natural workflow is a meeting-to-decisions skill …
OpenAI's video model: text or image in, short clip out, with storyboard control.
Google DeepMind's video model, available through Gemini and Vertex AI.
Kuaishou's video generator, tuned for motion and image-to-video.
Turn a script into a shot list a camera or a model can follow.
Align subtitles to speech without drifting.
Reframe horizontal footage for vertical without cutting the subject.