Skip to main content
Glama

Supadata

by ai.supadata.api
OverviewDiscussionsAdmin

Get Video Transcript

supadata_transcript
Read-onlyIdempotent

Get the transcript (what is said) of a video or post on YouTube, TikTok, Instagram, X (Twitter) or Facebook, or of an audio or video file URL. Not for ordinary web pages: use supadata_scrape for those. For large files, returns a jobId instead of the transcript directly - use supadata_check_transcript_status with that jobId to poll for results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL of a single video or post on YouTube, TikTok, Instagram, X (Twitter) or Facebook, or a direct link to an audio or video file. Not for ordinary web pages (use supadata_scrape).
langNoPreferred transcript language as an ISO 639-1 code, e.g. "en". Falls back to the first available language.
modeNo"native" only fetches an existing transcript, "generate" always transcribes with AI, "auto" (default) tries native first and falls back to generate.
textNotrue returns the transcript as plain text; false (default) returns timestamped segments.
chunkSizeNoMaximum characters per timestamped segment (at least 50). Ignored when text is true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / chunkSize / description
      Added value: +"Maximum characters per timestamped segment (at least 50). Ignored when text is true."
    • addedInput schema / properties / chunkSize / minimum
      Added value: +50
    • addedInput schema / properties / lang / description
      Added value: +"Preferred transcript language as an ISO 639-1 code, e.g. \"en\". Falls back to the first available language."
    • addedInput schema / properties / mode / description
      Added value: +"\"native\" only fetches an existing transcript, \"generate\" always transcribes with AI, \"auto\" (default) tries native first and falls back to generate."
    • addedInput schema / properties / mode / enum
      Added value: +[
+  "native",
+  "auto",
+  "generate"
+]
    • addedInput schema / properties / text / description
      Added value: +"true returns the transcript as plain text; false (default) returns timestamped segments."
    • addedInput schema / properties / url / description
      Added value: +"URL of a single video or post on YouTube, TikTok, Instagram, X (Twitter) or Facebook, or a direct link to an audio or video file. Not for ordinary web pages (use supadata_scrape)."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: the dual return mode (transcript directly vs. jobId for large files) and the polling follow-up. It stops short of mentioning auth requirements, rate limits, or failure modes, so it is not maximally transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, zero filler, front-loaded with the core capability before the exclusion and the async caveat. Every sentence carries information an agent needs to select and call the tool correctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by explaining the two possible return shapes (transcript or jobId) and the follow-up tool needed for the latter. Combined with the platform coverage, the exclusion rule, and complete schema param docs, nothing essential for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents lang (ISO 639-1 + fallback), mode (native/auto/generate semantics), text (plain text vs timestamped segments), and chunkSize (minimum 50, ignored when text is true). The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Get the transcript ... of a video or post') and enumerates the supported platforms (YouTube, TikTok, Instagram, X, Facebook, plus direct audio/video file URLs). It also explicitly separates itself from supadata_scrape by naming the excluded resource type, so an agent can distinguish it from siblings without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-not ('Not for ordinary web pages: use supadata_scrape for those') with the alternative named. It also routes the async case: large files return a jobId and the agent should use supadata_check_transcript_status to poll, which is a clear conditional workflow rather than implied usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Supadata toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources