extract_structured_data
Use AI to extract structured data from video content. Analyzes what is seen and heard in the video (visuals, audio, context). Provide a natural language prompt, a JSON Schema for the output, or both. Always processes asynchronously — returns a job ID to poll for results. When only a prompt is provided, the AI auto-generates a schema which is returned for reuse.
get_media_metadata
Fetch metadata from videos and posts hosted on YouTube, TikTok, Instagram, X (Twitter), or Facebook. Returns a unified schema with platform, content type, author info, engagement stats, media details, tags, and creation date. For YouTube-specific detailed metadata, use the "Get YouTube Video" tool instead.
get_extraction_job_result
Retrieve the result of an asynchronous structured data extraction job. Use this when the "Extract Structured Data from Video" tool returns a job ID. Poll until the status is "completed" or "failed".
get_transcript_job_result
Retrieve the result of an asynchronous transcript job. Use this when the "Get Video Transcript" tool returns a job ID instead of immediate content. Poll this endpoint until the job status is "completed" or "failed".
get_transcript
Extract text transcripts from videos hosted on YouTube, TikTok, Instagram, X (Twitter), Facebook, or from direct file URLs (MP4, WEBM, MP3, WAV, etc.). Supports language preference, plain text or timestamped output, and multiple transcription modes (native captions, AI-generated, or auto). If the video requires async processing, a job ID is returned that can be polled for results.
crawl_website
Start an asynchronous crawl of a website to extract content from all its pages. Returns a job ID to poll for results. The crawler follows only child links — for example, crawling `https://example.com/blog` will follow `/blog/article-1` but not `/about`.
get_crawl_job_result
Retrieve the status and results of a website crawl job. Use this to poll for results after starting a crawl with the "Crawl Website" tool.
get_youtube_playlist
Fetch metadata and video list from a YouTube playlist. Returns playlist info (title, description, video count, etc.) and optionally the list of video IDs in the playlist.
get_youtube_video
Fetch detailed metadata for a specific YouTube video. Returns title, description, channel info, engagement stats, duration, thumbnails, and more. For metadata from other platforms (TikTok, Instagram, etc.), use the "Get Media Metadata" tool instead.
translate_youtube_transcript
Fetch and translate the transcript of a YouTube video into a target language. This is specific to YouTube and uses YouTube's built-in translation capabilities.
map_website
Scan a website and discover all URLs found on it. Useful for creating a sitemap, understanding site structure, or preparing a list of pages to crawl.
scrape_web_page
Extract content from any web page and receive it in clean markdown format. Returns the page content, name, description, and character count. Useful for converting web pages into structured text for processing or analysis.
get_youtube_channel
Fetch metadata and video list from a YouTube channel. Returns channel info (name, description, subscribers, etc.) and optionally a list of video IDs. Combine channel metadata retrieval with video listing in a single tool.
search_youtube
Search YouTube for videos, channels, and playlists. Supports filtering by type and sorting by relevance, date, view count, or rating.
Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.
Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.
Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.
Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.
Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Track issues with the built-in issue tracker. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.
Deploy, manage, and scale applications on Heroku's cloud platform. Create and configure apps, scale dynos, provision add-ons (databases, caching, etc.), manage configuration variables, build and release code, add custom domains and SSL certificates, manage collaborators and team permissions, configure pipelines for continuous delivery, set up log drains, and sync data with Salesforce via Heroku Connect. Subscribe to webhooks for real-time notifications on app changes, builds, releases, dyno lifecycle events, and more.
Extract video transcripts, media metadata, and web page content as structured text and data. Transcribe videos from YouTube, TikTok, Instagram, Facebook, and X (Twitter) with language preferences and timestamped or plain text output. Fetch unified media metadata including engagement stats, author info, and platform-specific details. Use AI to extract structured data from video content via natural language prompts and JSON schemas. Scrape any web page into clean markdown, map website URLs, and crawl entire websites with configurable page limits. Search YouTube for videos, channels, and playlists, retrieve channel and playlist metadata, list channel or playlist video IDs, and translate YouTube transcripts into target languages.
Common questions about connecting Supadata to AI agents with Metorial.
