iveo produce

Who's speaking? Your AI-powered production knows instantly.

Local AI-powered speaker recognition for live events. The local AI identifies speakers in real time via camera and assigns them automatically to the running programme — without cloud, GDPR-compliant.

Version v1.7.0 · Last updated: March 2026

iveo Speaker Detection – Real-time face recognition on a monitor with green bounding box and confidence score

Local AI — No Cloud Upload

The AI-powered face recognition runs entirely locally on your device. No data leaves your machine — maximum privacy, fully GDPR-compliant.

Real-Time Recognition

The local AI identifies speakers in under one second and automatically assigns them to the running programme — no manual intervention required.

Cross-Platform

Available for macOS (Intel & Apple Silicon) and Windows. Works with any USB camera and professional capture cards.

How It Works

From camera to live production — fully automatic

In five steps, the app identifies the active speaker and controls your event production in real time.

Backstage production at a live event with monitors and speaker recognition
1

Camera captures the stage

Connect a camera — USB webcam, built-in laptop camera or professional capture card. The app automatically detects all available cameras.

2

Local AI detects faces

The local AI (dlib HOG + ResNet 128D) analyses the camera feed in real time — directly on your device, without any cloud connection.

3

Speaker is identified

The local AI matches the detected face against reference images from the iveo platform — with configurable recognition threshold and confidence score.

4

Automatic assignment

The recognised speaker is transmitted to the iveo event platform in real time. The live production knows instantly who is speaking.

5

Programme changes automatically

When the programme changes during a live event, new speaker lists are loaded automatically — without manual intervention.

Features

Everything you need for local AI speaker recognition

Local AI Speaker Recognition

The local AI uses dlib HOG + ResNet 128D for face recognition — maximum performance with full data privacy, no cloud dependency.

Multi-Camera Support

USB webcams, built-in cameras and professional capture cards — Blackmagic, Magewell, Elgato, AJA, AVMatrix.

Manual Assignment

Click on a detected face in the live view to manually assign the speaker — as a fallback or correction.

Automatic Programme Polling

Programme changes are detected automatically. New speaker lists are loaded without the operator having to intervene.

Event History

Quick access to the last 5 events. No searching or setting up again — ready to go instantly.

Auto-Update

Automatically checks for new versions. Updates are downloaded in the background and installed with a single click.

Secure Licence System

Access via licence key. No API tokens on the device — authentication via secure AWS Lambda proxy.

Log Export & Support

Comprehensive logging with export function. Logs can be sent directly to iveo support.

Configuration

Fine-tuneable — for every stage situation

All parameters can be adjusted directly in the app to optimise recognition for your setup.

Parameter Default Description
Recognition threshold 0.55 How confident the recognition must be (0.0–1.0)
Cooldown 2.0s Minimum time between speaker changes
Recognition interval 800ms How often a frame is analysed
Programme polling 10s How often programme changes are checked
Download

Download now — free with licence key

Available for macOS and Windows. Always the latest version, with automatic updates.

macOS

Version v1.7.0
  • macOS 12.0+ (Monterey or later)
  • Intel & Apple Silicon (M1–M4)
  • ~500 MB storage
  • 2 GB RAM (4 GB recommended)
Download for macOS
Installation guide
  1. Download and unzip the ZIP file
  2. Drag the app to your Applications folder
  3. Right-click and select "Open" (first launch only)
  4. Enter your licence key — done!

Windows

Version v1.7.0
  • Windows 10+ (x64)
  • x64 processor, 2+ cores recommended
  • ~500 MB storage
  • 2 GB RAM (4 GB recommended)
Download for Windows
Installation guide
  1. Download and unzip the ZIP file
  2. Run iveo Speaker Detection.exe
  3. Confirm the Windows Defender warning
  4. Enter your licence key — done!

Camera Compatibility

USB Cameras Any UVC-compatible USB camera
Built-In Cameras Laptop cameras (MacBook, etc.)
Capture Cards Blackmagic, Magewell, Elgato, AJA, AVMatrix
Resolution 640x360 (min.) to 4K — 720p recommended
Changelog

Version History

All versions and detailed changelogs are available on GitHub Releases.

v1.7.0 March 2026
Latest Version

Latest stable release with all current features and improvements. Automatic updates directly from the app.

Integration

Seamlessly connected to the iveo platform

Speaker Detection is part of iveo produce — iveo's digital event production suite. The app communicates directly with the iveo event platform.

Conference stage with panel discussion — speaker detection identifies the active speaker
Camera
Speaker Detection
iveo Platform

Ready for automatic speaker recognition?

Download iveo Speaker Detection now and experience how automatic face recognition takes your live event production to the next level.