> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 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.

![Supadata logo](https://mintcdn.com/composio-preview/IA0_SoMcsWt17HEC/images/toolkits/supadata.svg?fit=max\&auto=format\&n=IA0_SoMcsWt17HEC\&q=85\&s=7f29384e1907b836665a112368f673d1)

* **Category:** audio & speech
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 20
* **Triggers:** 0
* **Slug:** `SUPADATA`
* **Version:** 20261101\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Get Account Information
>
> **Slug:** `SUPADATA_GET_ME`
>
> Retrieve organization details, plan information, and credit usage for the authenticated account. Use this to check account status, credit balance, and subscription plan.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Media Metadata
>
> **Slug:** `SUPADATA_GET_MEDIA_METADATA`
>
> Retrieve unified metadata for supported social-media content. Supports YouTube videos, TikTok videos, Instagram reels and posts, Twitter/X posts, and Facebook videos and posts. Engagement statistics may be cached for up to about 10 minutes. HTTP 429 responses are plan-dependent and can indicate either the request-rate limit or usage-credit quota was exceeded.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **url** `string` *required*
>
> URL of supported YouTube, TikTok, Instagram, Twitter/X, or Facebook media.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Video Transcript
>
> **Slug:** `SUPADATA_GET_TRANSCRIPT`
>
> Get 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 Some connections support only explicit mode=native on HTTPS YouTube video URLs; AI generation, file URLs, other platforms and job polling are unavailable there. 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
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per transcript (native YouTube transcripts only)
>
> **Discount:** 91
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Video URL from any supported platform (YouTube, TikTok, Twitter, Instagram, Facebook) or a file URL. Example: '[https://youtu.be/dQw4w9WgXcQ](https://youtu.be/dQw4w9WgXcQ)'
>
> **lang** `string`
>
> 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.
>
> **mode** `string ("native" | "auto" | "generate")`
>
> Transcript retrieval mode.
>
> **text** `boolean`
>
> When true, returns plain text transcript. When false, returns structured transcript with timestamps. Default is false.
>
> **chunkSize** `integer`
>
> Maximum characters per transcript chunk. Only applies when text=false (structured transcript mode). Use this to split long transcripts into manageable segments.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Transcript by Job ID
>
> **Slug:** `SUPADATA_GET_TRANSCRIPT_BY_JOB_ID`
>
> Get the status and results of an asynchronous transcript job by job ID. Requires your own Supadata connection.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Video Extraction Result
>
> **Slug:** `SUPADATA_GET_VIDEO_EXTRACTION_RESULT`
>
> Retrieve the status and result of a video extraction job using your own Supadata connection. Poll until completed or failed; polling is free and completed results expire after one hour.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> Extraction job ID returned when video extraction was started.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Web Crawl Result
>
> **Slug:** `SUPADATA_GET_WEB_CRAWL_RESULT`
>
> Poll a web crawl and retrieve its pages using your own Supadata connection. Polling is free; repeat while status is scraping and continue with the skip value when a next URL is returned.
>
> #### Input Parameters
>
> **skip** `number`
>
> Number of crawled pages to skip (minimum 0). To continue a paginated result, pass the skip value from the returned next URL.
>
> **job\_id** `string` *required*
>
> Crawl job ID returned when the web crawl was started.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Website URL Map
>
> **Slug:** `SUPADATA_GET_WEB_MAP`
>
> Crawl 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The URL of the website to crawl and extract all links from. Must be a valid HTTP/HTTPS URL.
>
> **lang** `string`
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Scrape Web Page
>
> **Slug:** `SUPADATA_GET_WEB_SCRAPE`
>
> Extract 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The URL of the webpage to scrape. Must be a valid HTTP/HTTPS URL.
>
> **lang** `string`
>
> ISO 639-1 language code to request content in (e.g., 'en', 'es', 'fr'). Defaults to 'en'.
>
> **no\_links** `boolean`
>
> If true, exclude Markdown links from the extracted content. Useful for cleaner text output.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Batch Result
>
> **Slug:** `SUPADATA_GET_YOUTUBE_BATCH_RESULT`
>
> Poll a YouTube transcript or video metadata batch using your own Supadata connection. Polling is free; repeat until completed or failed, and use limit and offset to page completed results; unfinished jobs can expire.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of results to return (1-500). Omit limit and offset to retrieve all results.
>
> **job\_id** `string` *required*
>
> Batch job ID returned by a transcript or video metadata batch request.
>
> **offset** `integer`
>
> Number of results to skip in submission order (minimum 0).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Channel Metadata
>
> **Slug:** `SUPADATA_GET_YOUTUBE_CHANNEL`
>
> Fetches 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **id** `string` *required*
>
> 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](https://youtube.com/@GoogleDevelopers)').
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Channel Videos
>
> **Slug:** `SUPADATA_GET_YOUTUBE_CHANNEL_VIDEOS`
>
> Tool 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **type** `string ("all" | "video" | "short" | "live")`
>
> 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
>
> **limit** `integer`
>
> 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
>
> **channel\_id** `string` *required*
>
> YouTube channel URL, handle (e.g., '@RickAstleyVEVO'), or channel ID (e.g., 'UC\_x5XG1OV2P6uZZ5FSM9Ttw')
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Playlist Metadata
>
> **Slug:** `SUPADATA_GET_YOUTUBE_PLAYLIST`
>
> Retrieve 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **id** `string` *required*
>
> YouTube playlist URL or ID. Supports various formats including full URLs (e.g., '[https://www.youtube.com/playlist?list=PLlaN88a7y2\_plecYoJxvRFTLHVbIVAOoc](https://www.youtube.com/playlist?list=PLlaN88a7y2_plecYoJxvRFTLHVbIVAOoc)') or just the playlist ID (e.g., 'PLlaN88a7y2\_plecYoJxvRFTLHVbIVAOoc').
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Playlist Videos
>
> **Slug:** `SUPADATA_GET_YOUTUBE_PLAYLIST_VIDEOS`
>
> Tool 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.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of video IDs to return. Default is 100, maximum is 5000.
>
> **playlistId** `string` *required*
>
> YouTube playlist URL or ID to fetch video IDs from. Can be a full playlist URL like '[https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf](https://www.youtube.com/playlist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf)' or just the playlist ID like 'PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get YouTube Video Metadata
>
> **Slug:** `SUPADATA_GET_YOUTUBE_VIDEO`
>
> Retrieve 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](https://youtube.com/watch?v=dQw4w9WgXcQ)').
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per request
>
> **Discount:** 91
>
> #### Input Parameters
>
> **video\_id** `string` *required*
>
> 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](https://youtube.com/watch?v=dQw4w9WgXcQ)'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search YouTube
>
> **Slug:** `SUPADATA_SEARCH_YOUTUBE`
>
> Search YouTube for videos, channels, or playlists by keyword. Returns matching content with metadata like titles, thumbnails, view counts, and channel information.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per results page (about 20 results)
>
> **Discount:** 91
>
> #### Input Parameters
>
> **type** `string ("video" | "channel" | "playlist")`
>
> Type of resource to search for. If not specified, returns all types. Options: 'video', 'channel', 'playlist'.
>
> **limit** `integer`
>
> Maximum number of results to return. Default is 10, max is 5000. Costs 1 credit per page of about 20 results.
>
> **query** `string` *required*
>
> The search query term to search on YouTube. Examples: 'python tutorial', 'cooking recipes', 'music videos'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Video Extraction
>
> **Slug:** `SUPADATA_START_VIDEO_EXTRACTION`
>
> Start asynchronous structured extraction from public videos on supported social platforms or public media files, using a prompt, schema, or both. Returns a job ID for polling and requires your own Supadata connection; files are limited to 200 MB and videos to 55 minutes.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Public YouTube, TikTok, Instagram, X (Twitter), or Facebook video URL, or a public MP4, WEBM, MP3, FLAC, MPEG, MPGA, M4A, OGG, or WAV file URL. Files may be at most 200 MB, and videos may be at most 55 minutes long.
>
> **prompt** `string`
>
> Nonblank natural-language description of what to extract. Required when schema is omitted. Do not put a JSON Schema in this field; use "schema" instead.
>
> **schema** `object`
>
> JSON Schema object defining the extracted data structure. Required when prompt is omitted; it may also be combined with prompt.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Web Crawl
>
> **Slug:** `SUPADATA_START_WEB_CRAWL`
>
> Start an asynchronous website crawl following child links under the supplied URL. Requires a Pro+ plan and your own Supadata connection; charges are estimated at submission and settled to the actual page count, and polling is free.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Top-level HTTP or HTTPS URL to crawl. The asynchronous crawler follows child links only. Respect the site's robots.txt and terms of service.
>
> **limit** `number`
>
> Maximum pages to crawl (1-5000). Omit this field to use the provider default of 100 pages.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start YouTube Transcript Batch
>
> **Slug:** `SUPADATA_START_YOUTUBE_TRANSCRIPT_BATCH`
>
> Start an asynchronous YouTube transcript batch from exactly one list of video IDs, playlist, or channel. Requires Supadata Pro or above and your own Supadata connection; unavailable transcripts remain billed, but videos failing for other reasons are not billed.
>
> #### Input Parameters
>
> **lang** `string`
>
> Preferred transcript language as an ISO 639-1 code. Supadata falls back to the first available language.
>
> **text** `boolean`
>
> When true, completed batch results contain plain-text transcripts; when false, they contain structured transcript chunks.
>
> **limit** `number`
>
> Maximum videos to process from a playlist or channel (1-5000). Omit for video\_ids; Supadata defaults to 10 for playlist and channel sources.
>
> **video\_ids** `array`
>
> Nonempty list of YouTube video IDs or URLs. Use exactly one source: video\_ids, playlist\_id, or channel\_id. Charged per requested video.
>
> **channel\_id** `string`
>
> Nonempty YouTube channel URL, handle, or ID. Use exactly one source. Regular videos are included; Shorts and live streams are skipped.
>
> **playlist\_id** `string`
>
> Nonempty YouTube playlist URL or ID. Use exactly one source. Regular videos are included; Shorts and live streams are skipped.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start YouTube Video Metadata Batch
>
> **Slug:** `SUPADATA_START_YOUTUBE_VIDEO_BATCH`
>
> Start an asynchronous YouTube video metadata batch from exactly one list of video IDs, playlist, or channel. Requires a Pro plan or above and your own Supadata connection; playlist and channel batches process regular videos only, and polling is free.
>
> #### Input Parameters
>
> **limit** `number`
>
> Maximum videos to process for a playlist\_id or channel\_id source (1-5000). The provider default is 10. Do not use this with video\_ids.
>
> **video\_ids** `array`
>
> Nonempty list of YouTube video IDs or URLs. Use this, playlist\_id, or channel\_id, but not more than one. Charged per requested video, settled to the actual result count when processing finishes.
>
> **channel\_id** `string`
>
> YouTube channel URL, handle, or ID. Use exactly one source. Channel batches include regular videos only, excluding Shorts and live streams.
>
> **playlist\_id** `string`
>
> YouTube playlist URL or ID. Use exactly one source. Playlist batches include regular videos only, excluding Shorts and live streams.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Translate YouTube Transcript
>
> **Slug:** `SUPADATA_TRANSLATE_YOUTUBE_TRANSCRIPT`
>
> Translate 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, and may take 20 or more seconds. HTTP 429 responses indicate a plan-dependent rate or usage limit was exceeded.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.01 per billable credit
>
> **Discount:** 91
>
> #### Input Parameters
>
> **url** `string`
>
> YouTube video URL. Provide exactly one of url or video\_id.
>
> **lang** `string` *required*
>
> Required ISO 639-1 language code for the translation.
>
> **text** `boolean`
>
> When true, return plain text. When false, return timestamped chunks. Defaults to false at the provider.
>
> **video\_id** `string`
>
> YouTube video ID. Provide exactly one of video\_id or url.
>
> **chunk\_size** `number`
>
> Maximum characters per chunk when text is false. Must be between 50 and 10000.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
