
robot_category: humanoid and social robot · intended_use: research and education
Data & sources
Key specifications

| Weight | 3.5 kg |
|---|---|
| Standing dimensions | 410 mm x 270 mm x 240 mm (H x W x D) |
| Total degrees of freedom | 3 DOF |
|---|---|
| Mask material | Furhat proprietary polymer blend |
| Servo count and type | 3 x high speed servos |
| Servo resolution | 0.088° resolution |
| Servo stall torque | 25 kg·cm |
| Modular subsystems | discrete modular subsystems |
| Replaceable mask | Furhat's swapable polymer magnetic mask |
| Power input | 19 V / 90 W |
|---|
| System architecture | open multimodal system |
|---|---|
| Controller type | Rotary thumbwheel controller |
| Cpu model | Intel Core i5 CPU |
| Cpu frequency | 3.40 GHz |
| Ram capacity | 8 GB |
| Storage capacity | 120 GB SSD |
| Gpu model | Iris Plus 640 GPU |
| Realtime api | Furhat Realtime API |
| Furhat sdk | Furhat SDK |
| Furhatai creator | FurhatAI Creator A zero-code LLM-driven conversation designer |
| Llm conversation automation | fully automate conversations by replacing your Furhat's NLU engine with any Large Language Model |
| Realtime api data streaming | Live-stream data between Furhat and your applications |
| Eye height | ~300 mm |
|---|---|
| Camera resolution | 3.4 MP; 640 x 480 pixels |
| Camera field of view | 120° |
| Microphone frequency response | 2 x 100 Hz ~ 10 kHz digital |
| Microphone spacing | 180 mm |
| Microphone array | 4 x MEMS omnidirectional digital mics |
| Vision field of view | 120° |
| Face detection | highly accurate face detection engine |
| Depth spatial perception | depth estimation, and spatial modelling |
| Audio localization | external USB multi-array microphone with noise cancelation and direction of arrival |
| Multi user tracking | up to 10 users |
| Face customization | customizable face |
|---|---|
| Gesture capability | customizable gestures |
| Facial expression capability | dynamic facial expressions |
| Projection brightness | 165 lumens |
| Voice library | vast library of voices in multiple languages |
| Projection resolution | 1280 x 720 |
| Projection contrast | 1400:1 |
| Speaker system | Dual speakers |
| Speaker power | 30 W |
| Wifi standard | 802.11ac WiFi, 2.4 / 5.0 GHz |
| Ethernet speed | Wired Ethernet Port - 10 / 100 / 1000 |
| Usb a ports | 2 x USB A supporting USB 3.0 |
| Usb c ports | 1 x USB-C⁵ |
| Led count | 88 RGB LEDs |
| Ambient temperature range | 5 - 25° C / 41 - 77° F °C |
| Ventilation clearance | 200 mm |
| High fidelity audio | High fidelity speakers with volume control |
| Connection ports | including an ethernet port, audio jack and USB ports |
| Facial rendering lip sync | real time high-fidelity rendering of dynamic facial expressions and lip-syncing |
| Automatic lip sync | automatic lip-syncing model |
| Facial gestures | gestures such as blinking, smiling, nodding, frowning |
| Languages and voices | 120+ languages; 200+ voices |
| Rapid turn taking | Rapid turn-taking |
01 · Official source
02 · Official source