Smart video conferencing for corporate meetings with HD PTZ cameras.
4k-ai-voice-tracking-ptz-camera-with-12x/20x-zoom-hdmi/usb/ip--poe, 4k-ai-voice-tracking-ptz-camera-with-12x/20x-zoom-hdmi/usb/ip--poe, /ptz-conference-camera
EN
4K AI Voice Tracking PTZ Camera
Features
• Auto Tracking
AI interaction, multi-gesture control, fast facial recognition & locking tracking
• Auto Frame
The camera will auto Zooming by the participants movements
• Full-Featured USB
Compatible with USB3.0 & USB2.0. supports audio, encoding output, UVC 1.1~1.5 protocols
• 4K Ultra HD
12x Sony 1/2.5" UHD CMOS sensor 8.51 million pixels,resolution 4K (3840x2160)
20x Sony 1/1.8" UHD CMOS sensor 8.42 million pixels,resolution 4K (3840x2160)
• 4 Microphone Arrays
4 Digital Microphone Arrays and 10 meters voice pickup,
Voice Tracking with Auto Zoom
Camera automatically rotates and tracks the voice with Auto Zoom
• HDMI 1.4b (optional)
Support HDMI 1.4, can directly output uncompressed 4K original video
• 71° wide-angle lens + 12x/20x optical zoom
Real 8 million ultra-high resolution 4K lens, 12x optical zoom, horizontal 12x/FOV 71°, 20x/FOV 60°
• Low illumination
Image noise reduce CMOS sensor in low illumination conditions, 2D and 3D noise reduction algorithms, Image signal-to-noise ratio is above 55dB
• Support POE
Support POE (Power Over Ethernet),to control, supply power, video & audio transmission through a network cable
• Remote control
Multi way of control, using RS232 (RS485 optional) serial ports,internet and USB to control the camera
• H.264 Slice/ H.264 SVC encoding support
Output H.264 stream supports Slice and SVC encoding modes, suitable for USB video conference
• Dual stream
Supports two-channel code stream output(any two of YUY2, MJPEG, H.264) to reduce the pressure of host encoding and decoding
• Rich and complete interface
Supported HDMI,USB3.0,RS232,RS485,4K video can be output at the same time.
• 3 ways of power supply
Support USB 5V power supply, 12V Adapter and PoE power supply
Key Features:
· Image Sensor & Resolution: 4K Ultra HD (3840×2160 @ 30fps) with Sony CMOS sensors – choose 12x (1/2.5″, 8.5MP, F1.8–F2.6, 71°–8.2° horizontal FOV) or 20x (1/1.8″, 8.42MP, F1.58–F3.95, 60°–3.5° horizontal FOV). Both deliver stunning clarity.
· PTZ Mechanism: Pan ±170° (max 35.7°/s), Tilt -30° to +90° (max 31.5°/s), with 255 preset positions (0.1° accuracy).
· Audio: 4-digital microphone array (linear, 45.8mm spacing) with 180° horizontal pickup, up to 10 meters voice capture, SNR 65.5dB, full-duplex, 16K/48KHz sampling.
· AI-Powered Intelligence:
· Voice Tracking & Auto Zoom – Camera automatically rotates toward the active speaker and zooms in/out.
· Auto Framing – Adjusts zoom to fit all participants in the frame.
· Gesture Control – Supports multi-gesture commands (tracking start/stop, zoom in/out).
· Humanoid (Facial) Tracking (optional) – locks onto and follows a moving subject
Selling Points:
1. True 4K Clarity with Optical Zoom – Sony sensors and 12x/20x optical zoom capture every detail – from wide room shots to close-ups – without digital degradation.
2. Intelligent AI Auto-Tracking – Voice tracking, auto-framing, and gesture control make it effortless to follow speakers or presenters, perfect for lectures, meetings, and live events.
3. Studio-Quality 4-Mic Array – 10-meter pickup and 180° coverage deliver crystal-clear, full-duplex audio – eliminating the need for external mics.
4. All-in-One Connectivity – HDMI, USB3.0, and IP (with PoE) outputs plus RS232/RS485 give you ultimate flexibility for any production or conferencing setup.
5. PoE & Triple Power Options – One Ethernet cable for power, video, audio, and control – simplifies installation and reduces cabling.
6. Dual-Stream & Advanced Encoding – H.264 SVC/Slice and dual-stream output reduce host decoding load, ensuring smooth performance on older PCs.
7. Seamless Integration – Supports ONVIF, RTMP(S), SRT, and VISCA/Pelco protocols – works with Zoom, Teams, OBS, vMix, and professional softwares.
8. Professional PTZ Performance – Wide pan/tilt range, high-speed presets, and 0.1° accuracy allow precise camera moves for dynamic presentations.
9. Low-Light Excellence – High-sensitivity sensor with advanced 2D/3D noise reduction ensures clean, bright images even in dim lighting.
10. Gesture Control & Remote Operation – Control tracking and zoom with simple hand gestures – intuitive and touch-free – ideal for hygienic environments










Moertek introduces the 4K AI Voice Tracking PTZ Camera with 12x/20x Zoom, HDMI/USB/IP & PoE, a premium AI PTZ camera engineered for modern meeting rooms, lecture halls, telemedicine suites, and hybrid learning environments. This voice-tracking camera combines industry-leading imaging, intelligent audio-driven auto-tracking, versatile connectivity, and Power over Ethernet convenience into a single 4K conference camera platform.
Product Overview and Core Capability
The Moertek AI PTZ camera integrates high-resolution optics with advanced voice detection to produce a responsive voice-tracking camera that captures participants with precision. As a 4K conference camera, it supports ultra-high-definition video up to 3840x2160 resolution, providing crisp detail for remote participants, recordings, and visual archives. The AI PTZ camera’s motorized pan, tilt, and smooth zoom mechanics, available in 12x and 20x optical zoom variants, allow close-ups, wide shots, and dynamic framing without sacrificing image quality.
Voice-Driven Auto-Tracking Intelligence
At the heart of the product is the voice-tracking camera algorithm that fuses microphone array input and visual analytics. The AI PTZ camera detects the active speaker direction through beamforming and time-difference-of-arrival processing, then commands the PTZ mechanism to follow the speaker smoothly and accurately.
Advanced Imaging and Optical Performance
The Moertek 4K conference camera features a high-quality image sensor paired with precision glass optics to maximize low-light capability, dynamic range, and color fidelity. The AI PTZ camera benefits from noise reduction and HDR processing to handle challenging lighting conditions, ensuring the voice-tracking camera outputs clean images across a variety of environments
Security, Compliance, and Reliability
Engineered with enterprise requirements in mind, the 4K conference camera incorporates secure network protocols, firmware signing, and access control mechanisms. The AI PTZ camera adheres to CE, FCC, and RoHS certifications and conforms to Moertek’s quality assurance benchmarks for long-term reliability. Redundant control pathways (serial, IP, and web UI) provide administrators with multiple ways to manage the PoE HDMI USB IP camera, minimizing downtime in mission-critical environments such as telemedicine and corporate boardrooms.

| Camera | Video resolution | HDMI(optional): 4KP29.97fps, 4KP25, 1080P30, 1080P29.29, 1080P25 |
| Scanning Mode | Progressive Scan | |
| Sensor 12x Lens |
1/2.5", CMOS, Effective Pixel: 8.5M 12x: f=4.4mm~52.8mm, F1.8~F2.6 Horizontal: 71°~82°, Vertical: 42.7°~4.5° |
|
| Lens 20x Lens |
1/1.8", CMOS, Effective Pixel: 8.42M 20x: f=6.25mm~125mm, F1.58~F3.95 Horizontal: 60°~3.5°, Vertical: 35.7°~2.0° |
|
| Minimal Illumination | 0.5 Lux@(F1.8, AGC ON) | |
| Digital Zoom | 16x | |
| Shutter | 1/30s~1/10000s | |
| White Balance | Automatic, indoor, outdoor, one-button, manual, specified color temperature | |
| Backlight Compensation | Support | |
| Digital Noise Reduction | 2D&3D Digital Noise Reduction | |
| Signal-to-noise ratio | ≥55dB | |
| Horizontal Rotation Range | ±170° | |
| Vertical rotation range | -30°~ +90° | |
| Pan Speed Range | 2.7°~35.7°/s | |
| Tilt Speed Range | 2.7°~ 31.5°/s | |
| H&V Flip | Support | |
| Image Freeze | Support | |
| PoE power supply | Support | |
| Humanoid tracking | Support (optional) | |
| Number of Preset | 255 | |
| Preset Accuracy | 0.1° | |
| USB features | Support operating system | Windows 7, Windows 8, Windows 10, Mac OS X, Linux, Android |
| Color space/compression | YUY2/MJPEG/ H.264 | |
| Video format | MJPEG: 2160P@30fps(max) H.264 AVC: 2160P@30fps(max.) YUY2: 1440P@30fps(max.) |
|
| USB audio | Support | |
| USB video communication protocol | UVC 1.1 | |
| UVC PTZ control | Support | |
| Microphone | MIC Array Quantity | 4 |
| MIC Array Form | linear | |
| Microphone Spacing | 45.8mm | |
| Sampling Rate | 16KHz/48KHz | |
| Sensitivity | -26dBFs | |
| Pick up Voice Distance | 0-10meters | |
| Voice Pick up Angle | Horizontal 180° | |
| SNR | 65.5dB | |
| Communication Mode | full duplex | |
| Network characteristics | Video coding standard | H.264/MJPEG |
| Video stream | The first stream, the second stream | |
| Resolution of the first stream | 3840×2160, 2560×1440, 1920×1080, 1280×720, 1024×576 | |
| Resolution of the second stream | 1920×1080, 1280×720, 720×576, 720x480, 320x240 | |
| Video bitrate | 32kbps~102400kbps | |
| Rate control | Variable bit rate, fixed bit rate | |
| frequency | 50Hz: 1fps~ 50fps, 60Hz: 1fps~60fps | |
| Audio compression standard | AAC | |
| Audio bit rate | 96Kbps, 128Kbps, 256Kbps | |
| supporting agreement | RTSP, RTMP(S), ONVIF, DHCP, SRT (MJPEG format is not supported), Multicast, etc. | |
| INPUT/OUTPUT INTERFACE | HD output | 1xHDMI 1.4b |
| Network Interface | 1×NET: 10M/100M Adaptive Ethernet Ports | |
| audio port | 1 channel, 3.5mm, Audio In; 1 way, Line Out; | |
| USB interface | 1 way, Type-C socket, can output up to 4K@30fps compressed video and 1080P original video; | |
| Communication Interface |
1× RS232 IN: 8pin Min DIN, Max. Distance: 30m, Protocol: VISCA/Pelco-D/ Pelco-P 1×RS485: 2pin phoenix port; Max. Distance: 1200m; Protocol: VISCA/Pelco-D/ Pelco-P |
|
| Power connector | JEITA type (DC IN 12V) | |
| GENERIC SPECIFICATION | Input voltage | DC 12V/PoE (802.3af) |
| Input Current | 1.0A (max) | |
| Operating temperature | -10~ 40℃ | |
| Stored temperature | -40~60℃ | |
| Power consumption | 12W (max.) | |
| size | 169mm×142mm×164mm | |
| weight | 1.35Kg |
4K AI Voice Tracking PTZ Camera
Features
• Auto Tracking
AI interaction, multi-gesture control, fast facial recognition & locking tracking
• Auto Frame
The camera will auto Zooming by the participants movements
• Full-Featured USB
Compatible with USB3.0 & USB2.0. supports audio, encoding output, UVC 1.1~1.5 protocols
• 4K Ultra HD
12x Sony 1/2.5" UHD CMOS sensor 8.51 million pixels,resolution 4K (3840x2160)
20x Sony 1/1.8" UHD CMOS sensor 8.42 million pixels,resolution 4K (3840x2160)
• 4 Microphone Arrays
4 Digital Microphone Arrays and 10 meters voice pickup,
Voice Tracking with Auto Zoom
Camera automatically rotates and tracks the voice with Auto Zoom
• HDMI 1.4b (optional)
Support HDMI 1.4, can directly output uncompressed 4K original video
• 71° wide-angle lens + 12x/20x optical zoom
Real 8 million ultra-high resolution 4K lens, 12x optical zoom, horizontal 12x/FOV 71°, 20x/FOV 60°
• Low illumination
Image noise reduce CMOS sensor in low illumination conditions, 2D and 3D noise reduction algorithms, Image signal-to-noise ratio is above 55dB
• Support POE
Support POE (Power Over Ethernet),to control, supply power, video & audio transmission through a network cable
• Remote control
Multi way of control, using RS232 (RS485 optional) serial ports,internet and USB to control the camera
• H.264 Slice/ H.264 SVC encoding support
Output H.264 stream supports Slice and SVC encoding modes, suitable for USB video conference
• Dual stream
Supports two-channel code stream output(any two of YUY2, MJPEG, H.264) to reduce the pressure of host encoding and decoding
• Rich and complete interface
Supported HDMI,USB3.0,RS232,RS485,4K video can be output at the same time.
• 3 ways of power supply
Support USB 5V power supply, 12V Adapter and PoE power supply
This is a title description that can briefly introduce the module.
Our advanced video conferencing and audio solutions stand out with superior image quality, intelligent tracking, real-time noise reduction, and seamless multi-device compatibility, delivering optimized performance for modern business collaboration.
Empower conference rooms, classrooms, and live streaming with our advanced PTZ cameras, webcams, and microphone systems. Seamlessly adaptable for multiple use cases and professional deployments.