Skip to main content
Glama

omniseek_transcribe

Read-only

Transcribe spoken content from video, podcast, or audio URLs using local speech recognition. Optionally process only a time slice and return timestamps or speaker labels.

Instructions

Transcribe the SPOKEN content of a video / podcast / audio URL via local SenseVoice ASR (bilibili, xiaoyuzhou, direct audio). YouTube captions come from omniseek_read instead.

Tool name: omniseek_transcribe (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_transcribe".

Slow on the first call for a long item, then cached. For a long episode take the chapter from the shownotes and transcribe only that slice.

Args: url: the video, podcast or audio URL. language: "" auto-detects; "zh" / "en" skip detection. start: slice start, seconds or MM:SS / HH:MM:SS. duration: slice length, same forms. segments: also return [{start, end, text}] per segment (an extra pass). diarize: who said what: segments carry speaker labels (Chinese-focused, heavier; supersedes segments). speakers: known speaker count for diarize (0 = auto; pass it when you know it).

Returns {url, transcript, chars, audio_seconds, asr_seconds, source, title, cached, start_seconds?, duration_seconds?, segments?, speakers?}, or {url, error, transcript: ""} when no audio resolved. Repeating the same call while it runs attaches to that run; still running gives {status: "running", already_running: true, running_seconds, phase, note}: call again later. Over the machine's transcription limit it is queued and runs without you: {status: "queued", queue_position, note}; call again later with the same arguments. More: omniseek docs/TOOLS.md, omniseek_transcribe.

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": "omniseek_transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
startNo
diarizeNo
durationNo
languageNo
segmentsNo
speakersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnlyHint annotation it discloses first-call latency, caching of results, attach-to-running-run behavior, queueing above a machine transcription limit, and the error return when no audio resolves. Diarize is flagged as heavier and as superseding segments. The only shortfall is that 'the machine's transcription limit' and the actual cost/latency magnitudes stay unspecified.

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 the one-line purpose and the sibling exclusion, then cleanly sectioned into Args and Returns, so it is scannable despite its length. Some space goes to harness meta-text ('your MCP config adds its own prefix', 'Not in your tool list? ToolSearch') and a docs pointer, which is useful but not strictly definitional.

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

Completeness4/5

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

There is no output schema, and the Returns block compensates by enumerating the success shape, the no-audio error shape, and the two non-terminal status shapes (running, queued) with their fields. Combined with parameter and retry guidance this is nearly self-sufficient; only the transcription limit itself remains undefined.

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?

With 0% schema description coverage, the description carries the full burden and does so for all seven parameters: url, language ('' auto-detects, 'zh'/'en' skip detection), start and duration (seconds or MM:SS / HH:MM:SS), segments (an extra pass), diarize (speaker labels, Chinese-focused, supersedes segments), and speakers (0 = auto, pass when known). This adds format and interaction semantics the bare schema cannot convey.

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 ('Transcribe the SPOKEN content of a video / podcast / audio URL') plus the underlying engine (local SenseVoice ASR) and supported sources (bilibili, xiaoyuzhou, direct audio). It also explicitly excludes the adjacent case by naming the sibling that handles YouTube captions (omniseek_read), so the agent can route without opening any schema.

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 says when to use this versus omniseek_read ('YouTube captions come from omniseek_read instead'), and gives an operational recipe for long items: take the chapter from the shownotes and transcribe only that slice. It also covers retry semantics for in-progress and queued runs, which is exactly the when-to-call-again guidance an agent needs.

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