G
GetLLMs

Speaker Diarization

Discover Speaker Diarization, an advanced solution for audio segmentation and speaker identification. Let's explore what this AI model can do for you!

Platform: Replicate
Speaker IdentificationAudio SegmentationSpeech Analysis
15 runs
T4
License Check Required

🚀Function Overview

Segments audio inputs by speaker and identifies when each speaker is active.

Key Features

  • Diarizes audio to distinguish between speakers
  • Allows control over speaker count min/max thresholds
  • Outputs segmented speaker timelines in URI format

Use Cases

  • Meeting transcription analysis
  • Podcast speaker segmentation
  • Call center conversation analytics

⚙️Input Parameters

audio

string

Audio file

num_speakers

integer

Number of speakers (if known)

min_speakers

integer

Minimum number of speakers

max_speakers

integer

Maximum number of speakers

💡Usage Examples

Example 1

Input Parameters

{
  "audio": "https://r2.getcastify.com/lex_ai_john_carmack_1.wav"
}

Output Results

https://replicate.delivery/czjl/WFWZi9guKrYhApMKxqnYKQEKKV5OfZ9f4O8LK6x3YFA4cLzUA/output.json

Quick Actions

Technical Specifications

Hardware Type
T4
Run Count
15
Commercial Use
Unknown/Restricted
Platform
Replicate

Related Keywords

Audio SegmentationSpeaker IdentificationSpeech AnalysisMeeting transcriptionPodcast speaker segmentationCall center conversation analyticsAudio analysis