Cancel a pending batch transcript job to stop further processing and get credits refunded for videos not yet started. Already fetched transcripts remain in results and stay paid for.
MCP server for multimodal understanding and object grounding (bounding boxes) across images, videos, and documents, with support for multiple AI providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint).
Use natural language queries to semantically search video collections and find relevant videos based on content, summaries, and metadata. Returns results with relevance scores.
Fetch video details, direct download link, and processing status for Meta ad videos. Poll until status is 'ready' to avoid thumbnail errors in creatives.