Skip to main content
Glama

Transcribe speech from a TikTok, podcast or media link

media_transcript
Read-only

Speech to text from a media link: TikTok, X, SoundCloud, Facebook, Dailymotion, podcasts, Drive or Dropbox links, direct audio or video files. Text, timestamped segments, language, duration; speaker labels on request. Price from maxMinutes (default 5, up to 120): direct file up to 25 MB $0.002 + $0.0006/min, other links $0.002 + $0.0009/min, speakers=1 $0.01/min. Longer media is refused unpaid. YouTube returns captions. No speech is a 404, not charged. Takes about 30 s; allow a 60 s timeout. Price: $0.0065 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged.

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": "media_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic link to the video, audio file or podcast episode (http or https)
languageNoSpoken language code such as en, tr or pt-BR (optional, detected by default)
speakersNo1 = label the speakers (optional; $0.01 per minute of maxMinutes)
maxMinutesNoLongest media to accept, 1 to 120, default 5. Sets the price: a direct audio or video file up to 25 MB $0.002 + $0.0006 per minute, other links $0.002 + $0.0009 per minute

Output Schema

NameRequiredDescriptionDefault
textNo
modelNo
titleNo
methodNo
sourceNo
languageNo
platformNo
segmentsNo
checkedAtNo
maxMinutesNo
source_noteNo
speakerLabelsNo
durationSecondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / maxMinutes / description
      Previous value: -"Longest media to accept, 1 to 120, default 5. Sets the price: a direct audio or video file up to 25 MB $0.001 + $0.0006 per minute, other links $0.002 + $0.0009 per minute"New value: +"Longest media to accept, 1 to 120, default 5. Sets the price: a direct audio or video file up to 25 MB $0.002 + $0.0006 per minute, other links $0.002 + $0.0009 per minute"
  2. Changed1 schema field changed
    • changedInput schema / properties / maxMinutes / description
      Previous value: -"Longest media to accept, 1 to 120, default 5. Sets the price: $0.0009 per minute (at least $0.002)"New value: +"Longest media to accept, 1 to 120, default 5. Sets the price: a direct audio or video file up to 25 MB $0.001 + $0.0006 per minute, other links $0.002 + $0.0009 per minute"
  3. Changed2 schema fields changed
    • changedInput schema / properties / maxMinutes / description
      Previous value: -"Longest media to accept, 1 to 120, default 10. Sets the price: $0.10 per started 10 minutes"New value: +"Longest media to accept, 1 to 120, default 5. Sets the price: $0.0009 per minute (at least $0.002)"
    • changedInput schema / properties / speakers / description
      Previous value: -"1 = label the speakers (optional)"New value: +"1 = label the speakers (optional; $0.01 per minute of maxMinutes)"
  4. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description carries the entire behavioral load and does so well — it discloses pricing formulas keyed to maxMinutes and file type, the speaker-label surcharge, payment rails (x402/USDC), that failed calls are not charged, refusal of over-length media, and the 404-on-no-speech rule.

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?

The platform list and output contents are front-loaded, which is good, but the single dense paragraph states pricing twice in potentially conflicting forms ('$0.002 + $0.0009/min' versus '$0.0065 per successful call'), which risks confusing the agent about actual cost. Several clauses ('Price from maxMinutes...', 'Price: ...') could be merged without losing information.

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?

For a paid, open-world transcription call it covers what an agent needs to invoke it correctly: accepted link types, output contents (text, timestamped segments, language, duration, speaker labels), cost model, latency/timeout expectations, and error semantics. An output schema exists, so the brief return-value mention is sufficient rather than required.

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 all four parameters are already documented in the schema, and much of the description's parameter text (maxMinutes bounds, speakers surcharge, language detection) restates it. It adds some real value by tying maxMinutes to the actual price tiers and the unpaid-refusal rule, but the extra meaning is modest over a fully documented schema.

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 and resource ('Speech to text from a media link') and enumerates the supported sources — TikTok, X, SoundCloud, Facebook, Dailymotion, podcasts, Drive/Dropbox, direct files. It also distinguishes its YouTube behavior ('YouTube returns captions'), which helps an agent separate it from the youtube_transcript sibling.

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?

Gives concrete operating conditions: media longer than the maxMinutes limit is refused unpaid, no-speech input returns 404, expect ~30 s and allow a 60 s timeout. It does not explicitly route the agent between this tool and siblings like transcribe or youtube_transcript beyond the captions note, so the alternative-selection guidance is partial rather than complete.

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