Skip to main content
Glama

Get AI-readable transcript

get_transcript

Transcribe speech from a public video, optionally between start and end. Returns a transcript_id while processing in the background: call this tool again with transcript_id to check. When done, fetch text_url for timestamped plain text with source attribution; Markdown and JSON links are also provided. Parts without speech are listed as machine-labelled sounds with times, closed-caption style (e.g. "[cat meowing]", "[music]"). Visual content is not described. New transcription uses the normal daily quota; results last 30 days.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOptional: end of the part to keep, in seconds (after start).
urlNoLink to a public post or video (YouTube, Instagram, X / Twitter, TikTok, Bluesky, Facebook, VK, LinkedIn, Weibo).
itemNoWhich video of a multi-video post (1-based); see get_video_info.
startNoOptional: start of the part to keep, in seconds.
transcript_idNoResume/check an existing transcription.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses traits the agent could not otherwise know: the job runs in the background, a new transcription consumes the normal daily quota, results persist for 30 days, non-speech segments are machine-labelled sound tags in closed-caption style, and visual content is explicitly not described. The quota and retention facts are exactly the kind of cost/limit context an agent needs before triggering a job.

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?

The description is front-loaded with the core action, then immediately covers the async return contract and the follow-up step before secondary details about output formats, sound labels, and quota. Sentences are tight and each carries distinct information (workflow, output, cost), with no filler or restatement of the tool name.

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

Completeness4/5

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

There is no output schema, and the description compensates well by naming the return fields (transcript_id, text_url, Markdown and JSON links) and explaining the polling loop. Coverage of what a transcription result contains and how long it lasts is solid for this complexity; only minor gaps remain, such as what happens if the URL is unsupported or the video has no speech at all.

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%, so all five parameters (url, item, start, end, transcript_id) are already documented, which sets the baseline at 3. The description reinforces the start/end window as an optional clip and clarifies that transcript_id is used to resume or poll, but the schema already says "Resume/check an existing transcription," so the added meaning is marginal rather than substantive.

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?

"Transcribe speech from a public video, optionally between start and end" states a specific verb (transcribe), a specific resource (public video speech), and a scope (time range). This clearly separates it from siblings such as get_video_info and download_video, and the async transcript_id flow is stated up front so the agent knows the tool is job-oriented rather than a one-shot fetch.

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

Usage Guidelines4/5

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

The description gives clear operational guidance for the two-phase workflow: the first call starts a background transcription and returns a transcript_id, and re-calling with that id checks status. It also says to fetch text_url once done and points to get_video_info via the schema for multi-video posts. It does not explicitly exclude alternatives (e.g., when to prefer get_video_info or download_video instead), which keeps it short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources