NexusScribe
AI-Powered Real-Time Transcription & Meeting Intelligence Platform
A self-hosted, enterprise-grade transcription platform that transforms meetings into actionable intelligence. Built for organizations requiring on-premises data sovereignty, it delivers real-time speech-to-text with speaker diarization, powered by local AI inference on CPU, CUDA GPU, or Hailo NPU.
For more information, contact us at devops@automatanexus.com
Download NexusScribe v1.0.0
Pre-built binaries or build from source
Linux x86_64 Binary
16 MB
Pre-built server and CLI binaries
Source Code
Full source
Full source code for custom builds
BSL-1.1 License
Free Use: Internal use, development, testing, and non-profit organizations
Commercial: Providing commercial transcription services requires a license agreement
Future: Converts to Apache-2.0 open source on January 26, 2030
Complete Meeting Intelligence
From live transcription to AI-powered insights, NexusScribe handles the entire workflow
Real-Time Transcription
Sub-200ms latency with Whisper models
Speaker Diarization
MFCC-based voice separation & identification
Meeting Intelligence
Summaries, action items, sentiment analysis
Live Collaboration
Operational transformation for real-time editing
Video Integration
Teams, Zoom, Google Meet, LiveKit support
Mobile App
Cross-platform iOS/Android with Expo SDK 54
Key Features
Multi-Backend Inference
CPU (64GB+ RAM), CUDA GPU, and Hailo NPU (8/10-H) compute backends with automatic language detection for 99 languages.
Enterprise Security
Role-based access control, multi-factor authentication (TOTP), JWT with refresh rotation, SOC 2 and HIPAA compliant audit logging.
AI Studio Tools
Edit for clarity, professional tone adjustment, filler word removal, auto-chapters, action item extraction, and speaker identification.
Export Formats
PDF, DOCX, JSON, SRT, and VTT exports with timestamp-linked commenting and version history with full audit trail.
Meeting Bot Integration
Automated bots join Microsoft Teams, Zoom, and Google Meet to capture audio and provide real-time transcription.
Aegis-DB Backend
Multi-paradigm database for users, meetings, transcripts (relational), audio metrics (time series), and topic relationships (graph).
Mobile App (React Native / Expo)
Cross-platform iOS and Android support with real-time transcription
Dashboard
Quick access to recording, meetings, AI Studio
Recording
Real-time audio level visualization
AI Studio
Waveform playback with editing tools
External Meetings
Connect bots to Zoom/Teams/Meet
Offline Mode
Queue actions, sync when online
Share & Export
TXT, JSON, PDF, DOCX formats
Data Flow
Audio Input → Preprocessing (16kHz mono, VAD) → Inference Engine →
Speaker Diarization → WebSocket Broadcast → Aegis-DB Storage →
Collaborative Editor → Export (PDF/DOCX/JSON/SRT)Technical Specifications
Performance Benchmarks
Ready for Enterprise Transcription?
Contact our team to learn how NexusScribe can transform your meetings into actionable intelligence with on-premises data sovereignty.
devops@automatanexus.com