Home / lattifai / lattifai-skills · GitHub

lai-diarize SKILL.md skillA

lai-diarize from lattifai/lattifai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add lattifai/lattifai-skills/lai-diarize@git:20260514.830b73a

Pins git:20260514.830b73a in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: lattifai/lattifai-skills
Path: skills/lai-diarize/SKILL.md
Versions recorded: 5
Latest version: git:20260514.830b73a, committed May 14, 2026
First version recorded: Apr 12, 2026
Size: 9,276 bytes
Repository stars: 32
License: MIT

Identify speakers ("who said what") in aligned captions via pyannote.audio. Real speaker names come from the agent's own reasoning over transcript + context (default), with a CLI-LLM fallback for headless runs. Trigger on multi-speaker content (podcasts, interviews, meetings) or phrases like "diarize", "speaker detection", "说话人识别", "区分说话人", "label the speakers". Requires aligned captions — run `/lai-align` first.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Speaker Diarization

> **Preferred model: Claude Sonnet** (cost-efficient for agent-driven naming). This skill runs on whatever model is active in the parent session — any Claude model works; no hard switch. Sonnet has no 1M-context variant, so if the parent session is Opus[1M], continuing on Opus is normal (avoids a no-op model swap).

Adds `speaker` labels to aligned captions. Speaker **detection** (who speaks when) is always CLI-based via pyannote.audio; speaker **naming** (who each one is) is agent-driven by default.

## Basic Command

`<base>` = source media stem (e.g. `podcast` from `podcast.mp3`) or YouTube ID. Files all land in the current directory:

```bash
lai diarize run podcast.mp3 podcast.aligned.json podcast.diarized.json
# shortcut:
lai-diarize podcast.mp3 podcast.aligned.json podcast.diarized.json
```

Output labels detected speakers as `SPEAKER_00`, `SPEAKER_01`, …

Speaker count is auto-detected. Override only when auto-detection is clearly wrong:

- `diarization.num_speakers=3` — exact count (when known)
- `diarization.min_speakers=N` / `diarization.max_speakers=N` — bound the search

## Giving Speakers Real Names

### Agent-driven (default)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add lattifai/lattifai-skills/lai-diarize@sha256:6178be7bccec9924

The line at the top of this page pins the label git:20260514.830b73a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_beimzlj6576tdb7u.svg)](https://markdownregistry.com/a/art_beimzlj6576tdb7u)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 12, 2026 and May 14, 2026, about one every 8 days.

version	committed	commit	size	audit
git:20260514.830b73a latest	2026-05-14	830b73a	9,276 B	A	view · diff
git:20260428.4ab9c84	2026-04-28	4ab9c84	4,764 B	A	view · diff
git:20260417.89d056b	2026-04-17	89d056b	7,645 B	A	view · diff
git:20260416.83f6907	2026-04-16	83f6907	4,558 B	A	view · diff
git:20260412.c7d541e	2026-04-12	c7d541e	3,862 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (9276 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

lattifai/lattifai-skills · 32 stars · license MIT · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_beimzlj6576tdb7u
GET https://markdownregistry.com/api/v1/resolve?ref=lattifai/lattifai-skills/lai-diarize
GET https://markdownregistry.com/api/v1/blob/6178be7bccec9924e6917ff6d42a8855e06900aed6a7c4b1570945b993421d0d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.