VoiceBM

LLM Voice Biometrics for Home Assistant

Local speaker identification. Zero cloud. Intelligence over convenience.

60-162x
Faster than WeSpeaker
<100ms
Embedding Generation
100%
Local Processing
Multi-Room
Passive Monitoring

Built for Intelligence

Next-generation voice biometrics powered by Sherpa-ONNX

Sherpa-ONNX Speed

Lightning-fast speaker recognition with neural network embeddings. Generate embeddings in under 100ms—60-162x faster than WeSpeaker.

🎯

Thing Engine

Sophisticated identity management with transform, merge, and alias operations. Handle complex family dynamics and voice variations seamlessly.

🏠

Multi-Room Deployment

Deploy passive nodes per room with RTSP audio capture. Identify speakers across your entire home with room-specific confidence scoring.

🔒

Privacy First

100% local processing. No cloud dependencies. Your voice data never leaves your network. Full control over enrollment and blocklists.

🤖

LLM Integration

Seamless integration with conversation.process and STT pipelines. Speaker tags appear naturally in transcripts for context-aware AI responses.

📊

Home Assistant Native

Full MQTT discovery. Per-person devices with blocklist controls. Global and per-room confidence sensors. Dashboard-ready enrollment interface.

See It In Action

Beautiful Home Assistant integration

Dashboard UI

Flask Dashboard

Web-based enrollment interface with real-time active pipeline monitoring and blocklist management.

HA Integration

Home Assistant Devices

Per-person and per-room devices with confidence sensors, voice detection, and threshold controls.

Live Detection

Real-Time Monitoring

Watch speaker identification happen in real-time across multiple rooms with confidence scoring.

Three Steps to Deploy

Get VoiceBM running in under 10 minutes

1

Extract & Setup

Run the automated installer wizard to configure your environment.

tar -xzf VoiceBM_v1.0_Complete.tar.gz
cd VoiceBM_v1.0_Complete
./setup_voicebm.sh
2

Deploy Global Services

Install the 10 global services and start the core system.

sudo cp config.json /home/user/voicebm/
cd scripts
sudo ./deploy_global_services.sh
3

Add Rooms

Deploy passive nodes for each room you want to monitor.

sudo ./replicate_node.sh living
sudo ./replicate_node.sh bedroom

Ready to Deploy?

Download the complete package and get started

v1.0 - Sherpa Edition

VoiceBM Complete Package

Download VoiceBM_v1.0_Complete.tar.gz

Size: 154KB | SHA256: 83db672d0761eee6100f7d3c8f569df99b540277925f73e4c42c9381d537de74

Includes: All templates, deployment scripts, documentation, and setup wizard

Get Live AI Support

Both AI assistants have complete VoiceBM documentation access

🤖

ChatGPT Assistant

Custom GPT with all VoiceBM documentation pre-loaded. Click and start chatting immediately—no setup required. Perfect for quick questions and troubleshooting.

💬 Chat with GPT Instantly
🧠

Claude (Anthropic)

Co-architect of VoiceBM. Quick 3-step setup loads all documentation automatically. Perfect for advanced customization, design philosophy, and complex questions.

🚀 Setup Claude Support

GPT: Instant access, pre-configured | Claude: 30-second setup, full flexibility