Skip to main content
Glama

omniseek_transcribe

Transcribe spoken content from any video, podcast, or audio URL into readable text. For long episodes, transcribe only the relevant chapter slice and add speaker labels when needed.

Instructions

Transcribe the SPOKEN content of a video / podcast / audio URL via local SenseVoice ASR (free, keyless, private, cached forever; chosen over Whisper after a real-audio benchmark — Whisper hallucinates on Chinese podcast intros). For the 干货-in-audio case where the substance is in the audio, not any text: bilibili videos (论文精读 / 方法论 / 读博 / 求职 talks), 小宇宙 podcasts, or any direct audio-file URL. (youtube already returns its captions via omniseek_read — no ASR needed; use that instead.)

THE LONG-EPISODE PATTERN: do NOT transcribe a 2-3h episode whole (30k+ chars nobody reads). Pull the chapter timestamps from the episode's shownotes (小宇宙 episode pages list them; use omniseek_search(query, sources=["xiaoyuzhou"], raw=True, full=True) / omniseek_read first), judge WHICH chapter matters, then transcribe just that slice: start="1:02:30", duration="12:00". Accepts seconds ("3750") or MM:SS / HH:MM:SS. Slices are also fast to start — on direct/enclosure audio only the slice region is downloaded. The flat transcript covers [start, start+duration] of the source audio. Pass segments=True to ALSO get a per-VAD-segment segments: [{start,end,text}] list (seconds) so a no-shownote episode becomes navigable / time-citable (the flat transcript is unchanged; segments costs an extra VAD + a batched re-transcribe pass, so request it only when you need the offsets).

Whole-item transcription remains right for short/dense items (a 10-min talk, a keynote clip); it is SLOW on first call for a long item, then cached forever. Reach for it deliberately on ONE item you've judged worth it, never as part of a broad sweep.

language: "" auto-detects; set "zh" / "en" to skip detection and sharpen accuracy when you already know the language.

diarize=True answers WHO said what (interviews / 对谈 / multi-host podcasts): segments become [{start,end,text,speaker}] with per-turn speaker labels and speakers gives the distinct count. It routes through a Chinese-focused diarization pipeline (Paraformer-zh + cam++ speaker clustering), a SEPARATE and heavier pass than the flat SenseVoice path, so request it only when the speaker turns matter, and expect zh accuracy (English audio is not its target). Cannot combine with plain segments (diarize supersedes it). speaker values are cam++'s cluster indices (0,1,2,...).

speakers=N pins the diarization to N speakers (the KNOWN head-count: a 1-on-1 interview = 2, a solo talk = 1, a 3-host panel = 3). PASS IT whenever you know the count: cam++'s automatic estimate is unstable on short / noisy slices and will over- or under-split, so pinning N is what makes the turns track reality. Leave it 0 (auto) only when the count is genuinely unknown. Ignored unless diarize=True.

Returns: {url, transcript, chars, audio_seconds, asr_seconds, source, title, cached, start_seconds?, duration_seconds?, segments?, speakers?} — or {url, error, transcript:""} if no audio resolved.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
startNo
diarizeNo
durationNo
languageNo
segmentsNo
speakersNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv0.2.0

TDQS

A4.9/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden — and it delivers comprehensively. It discloses the tool's safety/private profile (free, keyless, private, cached forever), performance traits (SLOW first call on long items, fast slice startup with region-only download), cost semantics (segments adds VAD + re-transcribe pass; diarize is a SEPARATE heavier pass), accuracy limitations (Chinese-focused diarization, English not its target), the Whisper hallucination rationale, and the error return shape. Contradicts nothing.

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?

The description is long but exceptionally dense — nearly every sentence carries a distinct fact, constraint, or heuristic, and it is front-loaded with the core purpose. It is well-structured with clear section headers (THE LONG-EPISODE PATTERN, return format). Some phrasing could be tightened ('nobody reads', the Whisper benchmark backstory), but the length is largely proportional to the tool's complexity: 7 params, zero schema descriptions, and intricate parameter interactions.

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?

Given the context signals — zero annotations, zero schema descriptions, no output schema, 7 parameters with complex interactions — this description is complete. It covers the full return shape (success and error variants), all parameter semantics, performance expectations, known limitations (diarize zh-accuracy), and strategic heuristics (pin speakers=N when known, transcribe only judged slices, never broad sweeps). An agent has everything needed to select and invoke this tool correctly.

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?

Schema description coverage is 0%, so the description is the only documentation — and it fully compensates. It explains all 7 parameters: url (source type), language ('' auto-detect, 'zh'/'en' skip detection), start/duration (seconds or MM:SS/HH:MM:SS, with concrete examples '1:02:30' and '12:00'), segments (per-VAD list, extra cost), diarize (speaker labels, cannot combine with plain segments), and speakers (pinning semantics, ignored unless diarize=True). Nothing is left undocumented.

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 opening sentence states a specific verb+resource+method: 'Transcribe the SPOKEN content of a video / podcast / audio URL via local SenseVoice ASR.' It distinguishes itself from siblings by explicitly naming the YouTube case ('youtube already returns its captions via omniseek_read — no ASR needed'), so the agent can tell it apart from omniseek_read and omniseek_search without opening schemas.

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?

Explicit when-to-use guidance is given: the 干货-in-audio case with concrete examples (bilibili 论文精读/方法论/读博/求职 talks, 小宇宙 podcasts, direct audio URLs). Explicit when-not-to-use is also given (YouTube → omniseek_read instead), plus a detailed long-episode pattern that routes through omniseek_search/omniseek_read for shownotes first and instructs never to transcribe a 2-3h episode whole. This is the gold standard for usage routing.

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

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/Battam1111/omniseek'

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