.png)
Aispeech
MT100
The MT100 device is equipped with advanced image processing algorithms, highlighted by AI-powered facial recognition technology. Its compact design helps optimize space for meeting rooms and teaching environments.
Main Features
AI Intelligent Audio-Visual Tracking Box designed for smart meeting rooms and hybrid meeting environments.
Automatically supports voice tracking and camera switching based on the active speaker.
Integrated AI facial recognition and video scheduling algorithms.
Supports simultaneous connection with multiple cameras and AISPEECH ceiling microphones.
Supports video output up to 4K@30fps.
Supports H.265 / H.264 / MJPEG video compression standards.
Supports video transmission via USB/UVC, HDMI, and network streaming.
Suitable for large meeting rooms, lecture halls, and hybrid meeting spaces.
Technical Specification
Device type: Central coordination processor for multi-device AI audio-visual tracking systems.
Device architecture: Dedicated hardware device integrated with a high-performance AI processing chip for facial and spatial recognition.
Processing technology: AI Facial Recognition, Intelligent Image Scheduling, and Audio-Visual Fusion Algorithm.
Key specifications: Supports simultaneous connection with up to 6 cameras and unlimited ceiling microphone arrays, with automatic camera switching based on the actual position of the active speaker.
Processing quality: Supports video processing and output at up to 4K @ 30fps.
Connectivity & networking: HDMI Input/Output, USB 3.0 (UVC/UAC), USB 2.0 Host, LAN RJ-45 (PoE), and TF card slot supporting up to 256GB.
System control: Advanced Web UI management interface with API support for third-party integration.
Power supply: DC 12V or PoE.
Installation & form factor: Compact design for mounting behind a display or inside a rack; optimized dimensions for space-constrained environments.
Supported standards: H.264/H.265, ONVIF, RTSP.
Product Overview
AISPEECH MT100 is an intelligent image processing device designed for modern meeting rooms that require automatic camera angle switching based on the active speaker. The device combines AI voice tracking with facial recognition to identify the speaker and automatically control the appropriate camera, creating a professional online meeting experience without manual operation.
With video processing capability of up to 4K@30fps, support for popular streaming standards, and flexible integration with AISPEECH ceiling microphones and third-party cameras, MT100 is a suitable solution for large meeting rooms, training halls, smart classrooms, and hybrid meeting spaces that require a high level of automation.
