Any Video to Text

Get video transcript

get_transcript

Idempotent

Get the full text of what is said in a public video from TikTok, YouTube, Instagram, Facebook or X. Uses the video's captions when it has them, otherwise speech-to-text, in the video's own language. Returns the title, author, platform, duration, source (captions or speech-to-text) and the transcript. A video that was transcribed before comes back at once. A new one takes from a few seconds to a few minutes; this tool waits up to about 45 seconds. If it is still running it returns a jobId: call transcribe_status with it to get the result. Cost: free accounts get a few new transcripts per day. Accounts with credits pay 1 credit per started 10 minutes of video and can do videos up to 2 hours. A video that is only music, private, removed or too long for the account comes back as an error with the reason.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

Name	Required	Description	Default
`url`	Yes	Link to one public video: a TikTok, YouTube (including Shorts), Instagram Reel/post, Facebook or X video URL.
`timestamps`	No	true to get one line per spoken segment, each starting with a [mm:ss] timestamp. Default false: plain text.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses the ~45 second wait ceiling, cache behavior, credit pricing per 10 minutes, the 2-hour cap, free-account quota, and the error conditions (music-only, private, removed, too long) with the reason returned. These are exactly the operational facts an agent needs before committing to a call.

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

Conciseness4/5

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

Front-loaded with purpose, then method, return shape, latency, async fallback, cost, and errors in a logical order. Dense but nearly every sentence carries decision-relevant information; only the cost/limit sentence runs long.

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 listing the exact return fields (title, author, platform, duration, source, transcript) and by explaining the jobId interim result. Nothing material is missing for a two-parameter read tool with a long-running backend.

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 coverage is 100%, so both parameters are already fully documented in the schema, including the timestamps flag's [mm:ss] format. The description adds nothing about either parameter, so 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 full text of what is said in a public video') and enumerates the supported platforms. It also distinguishes itself from the async sibling by naming transcribe_status as the polling path, so an agent can tell the two apart without opening a schema.

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?

Clear context for use: any public video URL from five platforms, captions preferred over speech-to-text, cached videos return instantly. It explicitly routes to transcribe_status when the call returns a jobId, but gives no guidance on when to prefer summarize_video over this tool.

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

All Any Video to Text tools Inspect

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

Need Help?