Supadata for AI agents

Agents read Supadata at once. Changes and sends are held for a person's approval by default.

About Supadata

Supadata is a web and video-to-text API that extracts transcripts from YouTube, TikTok, Instagram, Facebook, X (Twitter) and video files, retrieves social media metadata, and converts web content to markdown for AI training and content analysis.

What an agent can do in Supadata

Every Supadata action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.

Runs at once (reads)

Looks things up in Supadata without asking first. 14 actions.

  • Get Account InformationRetrieve organization details, plan information, and credit usage for the authenticated account. Use this to check account status, credit balance, and subscription plan.
  • Get Video TranscriptGet transcript from a video on supported platforms or from a file URL. Use this tool when you need to: - Retrieve transcripts from YouTube, TikTok, Twitter, Instagram, or Facebook videos - Extract tra
  • Get Transcript by Job IDGet results for a transcript job by job ID. Use this to retrieve results of asynchronous transcript processing. Check the status field to determine if the job is complete.
  • Get Video Extraction ResultRetrieve the current status and result of a video extraction job. Call this action repeatedly, waiting about one second between calls, until status is completed or failed. Polling is free. Completed r
  • Get Web Crawl ResultPoll a web crawl and retrieve its pages. Polling is free. Repeat while status is scraping; completed, failed, and cancelled are terminal. When next is returned, continue with the skip value from that
  • Website URL MapCrawl a website and extract all URLs/links found on it. Use this to create a sitemap, discover all pages of a website, or prepare for content scraping across multiple pages. Returns a list of all URLs
  • Scrape Web PageExtract content from any webpage and convert it to Markdown format. Use this tool when you need to: - Read and extract text content from a web page - Get metadata (title, description) from a webpage -
  • Get YouTube Batch ResultPoll a transcript or video metadata batch. Polling is free; repeat until status is completed or failed. An unfinished, abandoned job can age out with errorCode=job-expired. Use limit and offset to pag
  • Get YouTube Channel MetadataFetches metadata for a YouTube channel including name, description, subscriber count, video count, view count, and channel images. Accepts channel IDs, handles, or full YouTube URLs.
  • Get YouTube Channel VideosTool to retrieve video IDs from a YouTube channel. Returns lists of regular video IDs, YouTube Shorts IDs, and live stream IDs. Videos are ordered latest first. Use this to get video IDs that can be p
  • Get YouTube Playlist MetadataRetrieve metadata for a YouTube playlist including title, description, video count, view count, last updated timestamp, and channel information. Use this when you need playlist-level information. For
  • Get YouTube Playlist VideosTool to retrieve video IDs from a YouTube playlist. Returns lists of standard video IDs, YouTube Shorts IDs, and live stream IDs contained in the playlist.
Show all 14
  • Get YouTube Video MetadataRetrieve comprehensive metadata for a YouTube video by its ID. Use this tool when you need to get details about a specific YouTube video including: - Title, description, and tags - Channel information
  • Search YouTubeSearch YouTube for videos, channels, or playlists by keyword. Returns matching content with metadata like titles, thumbnails, view counts, and channel information.

Held for approval by default (changes and sends)

Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 6 actions.

  • Get Media MetadataRetrieve unified metadata for supported social-media content. Supports YouTube videos, TikTok videos, Instagram reels and posts, Twitter/X posts, and Facebook videos and posts. Each request costs one
  • Start Video ExtractionStart asynchronous structured extraction from a supported public video. Supadata analyzes what is seen and heard in public YouTube, TikTok, Instagram, X (Twitter), and Facebook videos or public media
  • Start Web CrawlStart an asynchronous website crawl. This Pro+ operation follows child links under the supplied URL. Respect the site's robots.txt and terms of service. Supadata charges one credit per crawled page: a
  • Start YouTube Transcript BatchStart an asynchronous YouTube transcript batch from exactly one list of video IDs, playlist, or channel. This feature requires Supadata Pro or above. Supadata charges one credit per requested video at
  • Start YouTube Video Metadata BatchStart an asynchronous YouTube video metadata batch. This feature requires a Pro plan or above and accepts exactly one source: video IDs, a playlist, or a channel. Playlist and channel batches process
  • Translate YouTube TranscriptTranslate a YouTube transcript into a requested ISO 639-1 language. Provide exactly one YouTube URL or video ID. This feature requires Supadata Pro or above, costs 30 credits per transcript minute, an

Changes wait in Needs you

Changes and sends in Supadata are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

How approvals work

Supadata questions

Can an agent change data in Supadata on its own?

Not by default. Changes and sends in Supadata are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

What can an agent read in Supadata?

This connector lists 14 read actions. Reads run at once, without waiting for approval.

How does Supadata connect?

It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.

Bring Supadata to your agents.