Skip to main content
Glama

Captapi

by io.github.CDCStream
OverviewDiscussionsAdmin

video_transcript

AI transcription of an uploaded file — 1 credit/min; noSpeech=true and 0 credits when there is no speech. Costs 1 credit/min. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

Input Schema

NameRequiredDescriptionDefault
fileYesVideo or audio file (multipart form field — use -F file=@path, not a query string). Max 200MB / 60 minutes.
languageNoISO-639-1 language hint, e.g. "en" or "tr". Omit to auto-detect.
translateNoWhen true, translate speech to English. Default false.
timestampGranularityNosegment (default) or word — word-level timings when the transcription model exposes them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / language / description
      Previous value: -"ISO-639-1 Whisper language hint, e.g. \"en\" or \"tr\". Omit to auto-detect."New value: +"ISO-639-1 language hint, e.g. \"en\" or \"tr\". Omit to auto-detect."
    • changedInput schema / properties / timestampGranularity / description
      Previous value: -"segment (default) or word — word-level timings when Whisper exposes them."New value: +"segment (default) or word — word-level timings when the transcription model exposes them."
    • changedInput schema / properties / translate / description
      Previous value: -"When true, translate speech to English (Whisper translations API). Default false."New value: +"When true, translate speech to English. Default false."
  2. Changed4 schema fields changed
    • changedInput schema / properties / file / description
      Previous value: -"Local path to video/audio — sent as multipart form field file (POST), not a query string."New value: +"Video or audio file (multipart form field — use -F file=@path, not a query string). Max 200MB / 60 minutes."
    • changedInput schema / properties / language / description
      Previous value: -"ISO-639-1 Whisper language hint, e.g. en or tr."New value: +"ISO-639-1 Whisper language hint, e.g. \"en\" or \"tr\". Omit to auto-detect."
    • changedInput schema / properties / timestampGranularity / description
      Previous value: -"segment (default) or word."New value: +"segment (default) or word — word-level timings when Whisper exposes them."
    • changedInput schema / properties / translate / description
      Previous value: -"Translate speech to English when true."New value: +"When true, translate speech to English (Whisper translations API). Default false."
  3. Changed4 schema fields changed
    • changedInput schema / properties / file / description
      Previous value: -"Local path or multipart file upload of the video/audio to transcribe."New value: +"Local path to video/audio — sent as multipart form field file (POST), not a query string."
    • addedInput schema / properties / language
      Added value: +{
+  "description": "ISO-639-1 Whisper language hint, e.g. en or tr.",
+  "type": "string"
+}
    • addedInput schema / properties / timestampGranularity
      Added value: +{
+  "description": "segment (default) or word.",
+  "type": "string"
+}
    • addedInput schema / properties / translate
      Added value: +{
+  "description": "Translate speech to English when true.",
+  "type": "boolean"
+}
  4. Added

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. It discloses cost (1 credit/min), the no-speech case (noSpeech=true, 0 credits) and that empty results/failures are never charged, which is genuinely useful. But it omits the output shape (no output schema exists), whether the call is synchronous or job-based, and what happens on files exceeding the 200MB/60min limits — critical gaps for a media-processing tool.

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

Conciseness3/5

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

Pricing is stated twice ('1 credit/min' and 'Costs 1 credit/min'), wasting a sentence. Otherwise the text is compact and front-loads the core purpose before the billing details.

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

Completeness3/5

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

For a file-upload tool with no annotations and no output schema, the description covers billing and caching well but leaves the return value, execution model (sync vs async), and error surface undocumented. An agent could call it, but could not predict what it gets back.

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

Parameters2/5

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

Schema coverage is 100%, so the baseline would be 3, but the description actively introduces a 'cache' parameter that does not exist in the input schema (additionalProperties is false), which could cause an invalid call. It adds nothing about language, translate, or timestampGranularity beyond the schema text.

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

Purpose4/5

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

States a specific verb+resource — 'AI transcription of an uploaded file' — and the word 'uploaded' implicitly separates it from URL-based siblings like youtube_transcript or tiktok_transcript. However, it never names those alternatives, so the agent must infer the distinction from the phrasing alone.

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

Usage Guidelines2/5

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

The cache guidance ('Pass cache=true for a free 24h cache hit') and the credit pricing do inform how to call it, but there is no explicit when-to-use versus the many *_transcript siblings, and no statement about when this upload tool is preferable to a platform-specific transcript tool.

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

All Captapi 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