diarization

Identify and label individual speakers in multi-speaker audio streams.

1|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/framerslab/agentos-skills --skill diarization
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: diarization
Source: https://github.com/framerslab/agentos-skills/tree/main/registry/curated/diarization
Command: npx skills add https://github.com/framerslab/agentos-skills --skill diarization

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires deepgram, spectral-centroid, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the identification and tracking of individual speakers in audio streams, making it easier to analyze and transcribe conversations.

Core Features & Use Cases

  • Speaker Identification: Recognizes and labels individual speakers in multi-speaker audio streams.
  • Transcription Support: Supports accurate transcription by enabling differentiation between speakers.
  • Use Case: Ideal for automated transcription of meetings, interviews, and other multi-speaker dialogues.

Quick Start

Apply diarization to an audio file 'meeting-discussion.mp3' and transcribe it automatically with speaker labels.

Frequently Asked Questions about diarization

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify and label individual speakers in a multi-speaker audio stream for transcription?

Speaker diarization identifies and tracks individual speakers in audio streams to support accurate transcription. By differentiating between speakers, it automates dialogue analysis for meetings and interviews.

Can I perform real-time speaker diarization on audio streams?

Yes, speaker diarization can be performed in real-time or offline from audio streams. Real-time processing enables immediate speaker identification for live audio transcription and dialogue analysis.

Do I need a speech-to-text service for speaker diarization?

Yes, speaker diarization requires access to an STT service for word-level labels or local clustering techniques. This integration ensures accurate speaker differentiation during the transcription process.

What is the best way to transcribe meetings with automated speaker recognition?

Applying speaker diarization to meeting audio is the best way to automate transcription with speaker labels. It recognizes individual speakers in multi-speaker audio to streamline dialogue analysis.

Does this speaker diarization process work with Deepgram?

Yes, the speaker diarization process works with Deepgram as a dependency. It utilizes the service alongside local clustering techniques to provide word-level labels for automated transcription.

Related Skills