TypingMindTypingMindThe best frontend for AI
Evo Diarization logo

Evo Diarization

Community
Zhang-Henry
evo-diarization

Speaker diarization and transcription pipeline for video files. Extracts audio, performs VAD with SpeechBrain, speaker embedding extraction with ECAPA-TDNN, data-driven clustering, and Whisper ASR. Produces RTTM, ASS subtitle, and JSON report files.

Overview

PublisherZhang-Henry
RepositoryCoEvoSkills
Skill nameevo-diarization
Stars
83
Forks
9
Bundled files
5
LicenseApache-2.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Zhang-Henry on GitHub. Read the source before you install it.

Installation

Install the Evo Diarization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Zhang-Henry/CoEvoSkills/tree/main/artifacts/skills/speaker-diarization-subtitles/evo-diarization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Zhang-Henry/CoEvoSkills.git /tmp/CoEvoSkills
mkdir -p .claude/skills
cp -r /tmp/CoEvoSkills/artifacts/skills/speaker-diarization-subtitles/evo-diarization .claude/skills/evo-diarization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Evo Diarization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Evo Diarization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Evo Diarization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Speaker Diarization Pipeline

This skill provides a complete speaker diarization and transcription pipeline.

Components

  • scripts/audio_extract.py - FFmpeg-based audio extraction (video -> 16kHz mono WAV)
  • scripts/diarize.py - SpeechBrain VAD + ECAPA-TDNN embeddings + silhouette-driven clustering
  • scripts/transcribe.py - Whisper-based per-segment transcription
  • scripts/output_gen.py - RTTM, ASS subtitle, and JSON report generators
  • scripts/pipeline.py - End-to-end orchestration with validation

Usage

python
import sys
sys.path.insert(0, '/app/environment/skills/evo-diarization/scripts')
from pipeline import run_pipeline, validate_outputs

# All paths are caller-supplied arguments
run_pipeline(
    video_path='<path-to-input-video>',
    rttm_output='<path-to-output-rttm>',
    ass_output='<path-to-output-ass>',
    report_output='<path-to-output-json>'
)
validate_outputs(
    '<path-to-output-rttm>',
    '<path-to-output-ass>',
    '<path-to-output-json>'
)

Pipeline Steps

  1. Extract 16kHz mono WAV from video using ffmpeg
  2. Run SpeechBrain VAD (vad-crdnn-libriparty) with model defaults to detect speech regions
  3. Extract ECAPA-TDNN speaker embeddings per segment
  4. Cluster embeddings using agglomerative clustering with cosine distance; threshold is auto-derived from the runtime embedding distribution via silhouette analysis
  5. Auto-detect cached Whisper model and transcribe each segment
  6. Generate RTTM, ASS subtitles (with SPEAKER_XX labels), and JSON report

Key Design Decisions

  • No hardcoded thresholds: VAD uses model defaults; clustering threshold is derived from runtime silhouette analysis over the observed embedding distances
  • Whisper model auto-detection: Scans cache directory and selects the best available model
  • All paths are caller-supplied: No artifact paths are embedded in the code
  • Consistent speaker labels: RTTM uses spkXX, ASS uses SPEAKER_XX, both derived from the same clustering output

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Evo Diarization AI skill do?

Speaker diarization and transcription pipeline for video files. Extracts audio, performs VAD with SpeechBrain, speaker embedding extraction with ECAPA-TDNN, data-driven clustering, and Whisper ASR. Produces RTTM, ASS subtitle, and JSON report files.

Why use Evo Diarization on TypingMind?

Because you install it once and use it with any model. Evo Diarization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Evo Diarization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Zhang-Henry/CoEvoSkills/tree/main/artifacts/skills/speaker-diarization-subtitles/evo-diarization. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Evo Diarization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Evo Diarization?

As many as you like. As long as a model supports skills, you can use Evo Diarization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Evo Diarization AI skill free?

Yes. It is published on GitHub by Zhang-Henry under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Camsnap

openclaw
OrganizationPopular

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

82.2K
391K
Instructions
View
affaan-m logo

Content Engine

affaan-m
CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

40.4K
270.2K
1 files
View
affaan-m logo

Fal Ai Media

affaan-m
CommunityPopular

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

40.4K
270.2K
1 files
View
affaan-m logo

Video Editing

affaan-m
CommunityPopular

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

40.4K
270.2K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇