Skip to main content
Glama
Sign In
Tapra MCP server

Tapra MCP server

Official
by tapra-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Transcribe audio

speech_to_text

Transcribe audio or video files containing mixed Tunisian Derja, French, and English, generating timed TXT, SRT, and VTT transcripts plus speaker labels.

Instructions

Transcribe an audio or video file with Tapra, which handles Tunisian Derja mixed with French and English. One call writes a folder with the transcript as txt, srt and vtt (plus a .json with full timings). Speakers are labelled by default (no extra charge): the result says how many were detected, with talk time, a quote and an audio clip of each, and a speakers.html page. When there are several speakers, ask the user whether to name them, then call name_speakers. Long files are split into chunks automatically. Costs money per minute of audio.

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": {
      "input_path": "<input_path>"
    },
    "name": "speech_to_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptNoNames, brands or jargon likely to appear, to help recognition.
diarizeNoFind who speaks when (no extra charge). Set false for a single speaker.
formatsNoFiles to write. Default: all three (txt, srt, vtt). A .json with full timings is always written too.
languageNoLanguage hint. Usually leave unset: code-switching is auto-detected.
input_pathYesPath to the audio or video file.
output_dirNoFolder to write into. Defaults to a new folder in the output folder.
max_cost_tndNoRefuse to run if the estimated cost is above this many TND. Defaults to TAPRA_MAX_COST_TND when set.
max_chars_per_subtitleNoLongest subtitle line in srt/vtt, in characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.3/5.0
Behavior5/5

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

Goes well past the annotations (which only say it is a non-idempotent, open-world, non-destructive write): it discloses that one call writes a whole folder of txt/srt/vtt plus a timings .json, that diarization is on by default at no extra charge with talk time/quotes/clips per speaker, that long files are chunked automatically, and that billing is per minute of audio. These are the side effects and cost facts an agent needs before invoking.

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 what the tool does and what it produces, then the naming workflow, then cost. Every sentence carries information, though the sentence enumerating speaker metadata and speakers.html is dense enough to slow a quick scan.

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 8 parameters, no output schema, and annotations that only cover the safety profile, the description fills the remaining gaps: what artifacts land on disk, what the speaker metadata looks like, how long inputs are handled, and the cost model. An agent can decide and call correctly without further probing.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3; the description adds real meaning on top by explaining the default-on speaker labelling (diarize), the default triple format output, and the per-minute cost driver behind max_cost_tnd. It says nothing extra about prompt, language, output_dir or max_chars_per_subtitle, so not a full 5.

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 and resource ('Transcribe an audio or video file') plus the differentiating input domain (Tunisian Derja mixed with French and English). It does not, however, explain how it differs from overlapping siblings such as transcribe_video or diarize_audio, so an agent still has to infer the boundary.

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 a concrete follow-up workflow — 'When there are several speakers, ask the user whether to name them, then call name_speakers' — which is real routing guidance, and warns about per-minute cost. It stops short of stating when to prefer diarize_audio or transcribe_video instead, so no explicit exclusions.

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

Deploy Server

Other Tools