Skip to main content
Glama
korovin-aa97

talkthrough-mcp

by korovin-aa97
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

process_media

Idempotent

Transcribes and indexes local video or audio files by validating the file, transcribing speech with Whisper, extracting keyframes, and OCRing text. Returns a compact summary for querying with other tools.

Instructions

Ingest a LOCAL video or audio file and make it queryable: validates the file, transcribes speech locally (whisper), extracts scene-change keyframes, OCRs on-screen text, and resolves the wall-clock start time. Returns a compact summary (job_id, media info, wall_clock, transcript preview) — full data stays on disk and is served lazily by the other tools. Idempotent by content hash: re-calling on an already-processed file returns instantly. When NOT to use: to re-fetch data you already processed (use the retrieval tools), or for URLs — local file paths only. Examples:

  • process_media(path="/Users/sam/Desktop/bug-repro.mov") — narrated screencast, defaults are right

  • process_media(path="~/Videos/demo.mp4", language="en") — pin the language, skip auto-detect

  • process_media(path="/rec/interview.mov", model="large-v3-turbo") — best multilingual quality (1.5 GB, one-time)

  • process_media(path="/tmp/standup.m4a") — audio-only: transcript tools work, frame tools will error

  • process_media(path="/rec/review.mov", vocabulary="OKR, PgBouncer, Kanban") — jargon survives STT

  • process_media(path="/rec/demo.mov", recorded_at="2026-07-10T12:03:00+02:00") — exact wall-clock anchor

  • process_media(path="/rec/demo.mov", recorded_at="2026-07-10T12:03:00+02:00", force=true) — re-anchor a done job

  • user: "I just recorded my screen, it's on my Desktop" → process_media(path="/Users//Desktop/.mov")

  • user drops a browser tab capture → process_media(path="~/Downloads/tab-capture.webm")

  • summary shows wall_clock=null → ask when recording started, re-call with recorded_at=... and force=true

  • transcript garbled or language_probability low → re-call with model="large-v3-turbo" (or language="ru") + force=true

  • 30-min video is fine: progress notifications stream while whisper runs; expect minutes, not seconds

  • after success, do NOT dump everything — continue with get_transcript / get_moment / search on the job_id

  • anti-example: frames from an already-processed job → get_frames(job_id=...), never process_media again

  • anti-example: YouTube/URL input → unsupported in v1; have the user download the file first

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
forceNo
modelNo
languageNo
vocabularyNo
recorded_atNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Tool Definition Quality

A4.9/5.0
Behavior5/5

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

Discloses idempotency by content hash, returns a compact summary, full data on disk, lazy serving, progress notifications, and expected duration. Aligns with annotations (idempotentHint=true).

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?

Well-structured with clear sections, examples, and anti-examples. Front-loaded with core purpose. Slightly lengthy but every sentence adds value.

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?

Covers return value, how to use subsequent tools, error handling for audio-only files, re-processing guidance. Accountable for complexity (6 params, multiple sibling tools). Output schema exists, reducing need for return value details.

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

Parameters5/5

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

Despite 0% schema description coverage, the description thoroughly explains each parameter through examples and context (e.g., path, force, model, language, vocabulary, recorded_at). Adds value beyond schema titles.

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?

The description clearly states the tool ingests a local video/audio file and makes it queryable, detailing the specific steps (validate, transcribe, keyframes, OCR, wall-clock). It distinguishes itself from sibling tools like get_frames and search.

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

Usage Guidelines5/5

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

Explicitly states when to use (local files) and when not to (URLs, re-fetching). Provides numerous examples covering various scenarios and mentions alternatives like retrieval tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/korovin-aa97/talkthrough-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server