MT200
AISPEECH MT200 Multimodal AI Audio-Visual Tracking Box
- Microphones
- Unlimited
- Connectivity
- Up to 8 concurrent 4K video…
Using ceiling microphone arrays and PTZ cameras, the AISPEECH MT200 follows the active speaker without camera presets. This AI audio-visual tracking box handles up to 8 concurrent 4K streams, accepts unlimited microphones and has a 6 TOPS NPU. It suits meeting rooms of 10 to 40 people, hybrid training rooms and classrooms across Qatar. Request a quote for a configuration matched to your room.
What the MT200 does in a room
The MT200 is a tracking box that sits between your microphones and cameras. It takes the sound location picked up by ceiling microphone arrays, combines it with the view from the connected PTZ cameras, and decides which camera should frame the person speaking. Because it works from the room itself rather than a list of saved positions, you do not have to program and maintain camera presets each time the seating changes.
AISPEECH positions it for larger meeting spaces, hybrid training rooms and standard classrooms. In each case the aim is the same: remote participants see the person who is talking, rather than a fixed wide shot that leaves them searching for the speaker.
Specifications worth checking before you order
- Video: up to 4K at 30 fps for both input and output, with up to 8 concurrent 4K streams.
- Outputs: 1 × HDMI IN and 2 × HDMI OUT, so one source can feed a local display and a second screen or recording device.
- USB: 1 × USB Device and 4 × USB Host ports for connecting peripherals.
- Network: 2 × RJ-45 ports, with one PoE port listed in the connectivity specification.
- Processing: 6 TOPS NPU for the AI speaker detection and tracking workload.
- Physical: 220 × 190 × 44.5 mm, net weight under 1.5 kg, Starlight Brown finish.
Where it fits in Qatar
Consider a 40-seat boardroom in West Bay where a management team regularly meets colleagues in Doha and abroad. Tracking can keep the speaker framed without a camera operator in the room. The MT200 is listed for meeting rooms of 10 to 40 participants, around 28 to 74 m² (300 to 800 sq ft).
A hybrid training room for 20 to 50 participants, around 60 to 149 m² (650 to 1,600 sq ft), is a strong case for presenter auto-framing across the room and dual-stream output for local and remote viewers. A training centre in Education City running sessions with participants in several locations would fit this profile.
In an ordinary classroom of 46 to 84 m² (500 to 900 sq ft), such as a private school in Al Wakrah or an Arabic-curriculum school in Al Rayyan, the MT200 can follow teacher movement, capture student interaction and record the whiteboard and display.
What to plan for before installation
- Confirm the PTZ cameras and ceiling microphone arrays you will connect, because the package contains the box, two brackets, six mounting bolts, a USB cable and the manual only.
- Check the power route. The MT200 is listed with PoE power, so confirm the network and PoE equipment at the installation point.
- Keep it in air-conditioned rooms. The operating range is 0°C to 40°C, and Qatar summer temperatures can exceed 45°C outdoors.
- Plan the mounting with the supplied brackets and bolts, and use a site survey to confirm the wall or ceiling position and camera sightline before drilling.
Request a quote for the MT200
Send your room dimensions, participant numbers and camera plan. The SmartRooms Qatar team will prepare a quotation, usually within one working day, covering supply, delivery to all eight municipalities of Qatar and professional installation. Request a quote for the MT200 today.
Highlights
- Preset-free speaker tracking using ceiling microphones and PTZ cameras
- Up to 8 concurrent 4K video streams
- Unlimited microphone connections
- 6 TOPS NPU for AI processing
- 1 × HDMI IN and 2 × HDMI OUT
- PoE power, under 1.5 kg, 220 × 190 × 44.5 mm
Room fit
Tell us the room size and platform (Teams, Zoom or BYOD) and we confirm the right combination with your quotation.
Estimated timeline
Quotation within 1 working day · delivery timing depends on stock availability, and we confirm it with your quotation.
Specifications
Basic3
- Product color
- Starlight Brown
- Product size
- 220 × 190 × 44.5 mm
- Power supply
- PoE
Video Processing3
- Video Input
- Up to 4K @ 30 fps
- Video Output
- Up to 4K @ 30 fps
- NPU Computing Power
- 6 TOPS
Connectivity8
- Camera Connectivity
- Up to 8 concurrent 4K video streams
- Microphone Connectivity
- Unlimited
- HDMI
- 1 × HDMI IN; 2 × HDMI OUT
- USB
- 1 × USB Device; 4 × USB Host
- Network
- 2 × RJ-45; 1 × PoE
- Audio Interfaces
- 1 × Line In, 1 × Line Out, 1 × Mic In, 3.5 mm (reserved)
- VGA
- 1 × VGA OUT, up to 1080p (reserved)
- TF Card
- 1 × Micro SD card slot (reserved)
Environment2
- Operating Temperature
- 0°C – 40°C
- Storage Temperature
- -20°C – 60°C