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.
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. On Nagent, Supadata is exposed as a fully-configurable ai web scraping integration that any agent can call — 11 actions, and API key authentication. No code is required to wire Supadata into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Supadata to automate the kinds of tasks ai web scraping teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Supadata into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Supadata, with input parameters and output schema. Drop these into any step of an agent built in Helix.
SUPADATA_GET_MERetrieve organization details, plan information, and credit usage for the authenticated account. Use this to check account status, credit balance, and subscription plan.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_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 transcript from video file URLs - Get transcripts in specific languages - Choose between native captions or AI-generated transcripts For large videos, the API returns a job ID. You'll need to poll the /transcript/{jobId} endpoint to get the final result. For smaller videos, the transcript is returned immediately. The response varies based on the 'text' parameter: - text=true: Returns plain text transcript as a string - text=false: Returns structured list of chunks with timestamps and text
Input parameters
Video URL from any supported platform (YouTube, TikTok, Twitter, Instagram, Facebook) or a file URL. Example: 'https://youtu.be/dQw4w9WgXcQ'
Preferred language code of the transcript (ISO 639-1 format like 'en', 'es', 'fr'). If not provided, the first available language will be returned. If the requested language is unavailable, the API defaults to the first available language.
Transcript retrieval mode.
When true, returns plain text transcript. When false, returns structured transcript with timestamps. Default is false.
Maximum characters per transcript chunk. Only applies when text=false (structured transcript mode). Use this to split long transcripts into manageable segments.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_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.
Input parameters
The unique job ID of the transcript job. This is returned when you submit a transcript request. Example: '41060930-5273-4a89-80a2-9ba5ea5bc03f'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_WEB_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 discovered during the crawl.
Input parameters
The URL of the website to crawl and extract all links from. Must be a valid HTTP/HTTPS URL.
Preferred language for the scraped content (ISO 639-1 code, e.g., 'en', 'de', 'fr'). Sets Accept-Language header to influence website language selection.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_WEB_SCRAPEExtract 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 - Discover links on a webpage - Get character counts of page content The tool returns the page content in Markdown format, making it easy to process and understand. One API credit is consumed per scrape request.
Input parameters
The URL of the webpage to scrape. Must be a valid HTTP/HTTPS URL.
ISO 639-1 language code to request content in (e.g., 'en', 'es', 'fr'). Defaults to 'en'.
If true, exclude Markdown links from the extracted content. Useful for cleaner text output.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_YOUTUBE_CHANNELFetches 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.
Input parameters
The YouTube channel identifier. Accepts multiple formats: channel ID (e.g., 'UC_x5XG1OV2P6uZZ5FSM9Ttw'), handle (e.g., '@GoogleDevelopers'), or full URL (e.g., 'https://youtube.com/@GoogleDevelopers').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_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 passed to the Get YouTube Video endpoint for full metadata.
Input parameters
Type of videos to retrieve: 'all' (default) returns all types, 'video' for regular videos only, 'short' for YouTube Shorts only, 'live' for live streams only
Maximum number of videos to return. Default is 30, maximum is 5000. When type is 'all', limit applies to regular videos first, then shorts and live videos
YouTube channel URL, handle (e.g., '@RickAstleyVEVO'), or channel ID (e.g., 'UC_x5XG1OV2P6uZZ5FSM9Ttw')
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_YOUTUBE_PLAYLISTRetrieve 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 the list of videos in a playlist, use the Get YouTube Playlist Videos action instead.
Input parameters
YouTube playlist URL or ID. Supports various formats including full URLs (e.g., 'https://www.youtube.com/playlist?list=PLlaN88a7y2_plecYoJxvRFTLHVbIVAOoc') or just the playlist ID (e.g., 'PLlaN88a7y2_plecYoJxvRFTLHVbIVAOoc').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_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.
Input parameters
Maximum number of video IDs to return. Default is 100, maximum is 5000.
YouTube playlist URL or ID to fetch video IDs from. Can be a full playlist URL like 'https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf' or just the playlist ID like 'PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_GET_YOUTUBE_VIDEORetrieve 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 - View and like counts - Upload date and duration - Live stream status - Available transcript languages The video_id is the 11-character identifier found in YouTube URLs (e.g., 'dQw4w9WgXcQ' from 'https://youtube.com/watch?v=dQw4w9WgXcQ').
Input parameters
The YouTube video ID (11-character string found in YouTube URLs after 'v=' or '/watch?v='). Example: 'dQw4w9WgXcQ' from 'https://youtube.com/watch?v=dQw4w9WgXcQ'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
SUPADATA_SEARCH_YOUTUBESearch YouTube for videos, channels, or playlists by keyword. Returns matching content with metadata like titles, thumbnails, view counts, and channel information.
Input parameters
Type of resource to search for. If not specified, returns all types. Options: 'video', 'channel', 'playlist'.
Maximum number of results to return. Default is 10, max is 5000. Note: Uses 1 credit per page (~20 results).
The search query term to search on YouTube. Examples: 'python tutorial', 'cooking recipes', 'music videos'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 51 agents privately built on Nagent that already use Supadata.
Build on Nagent
Connect Supadata to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Supadata, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Supadata is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Supadata is connected, you configure its 11 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Supadata steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Supadata event fires, the agent kicks off automatically.
Every Supadata action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Supadata ships with 11 pre-built ai web scraping actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Supadata together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Supadata-based workflows tailored to your business.