Apollo is an audio/visual AI engineering kit that is built around the NVIDIA® Jetson Xavier™ NX computing module, enabling developers to build applications with conversational AI capabilities. Apollo features four microphones, two speaker terminals, two 3.5mm phone jacks, an 8MP camera module, an OLED display, and a 128GB NVMe SSD.
Apollo is also pre-packaged with NVIDIA® JetPack, DeepStream, and RIVA on Embedded SDK toolkits and six natural language processing (NLP) examples demonstrating its unique capabilities.
Create excellent results in a variety of scenarios with Vision AI and next level natural language processing (NLP). Apollo helps engineers in integrating audio and vision AI to build state-of-the-art edge solutions to real-world problems.
A functional engineering kit for your audio/video AI development needs. Focus your efforts on developing edge AI audio-visual solutions rather than on enabling peripheral devices or ensuring successful system integration.
Includes several audio and video AI applications based on NVIDIA® DeepStream and RIVA that work out-of-the-box. New examples will be added on a regular basis.
NVIDIA® JetsonXavier™ NX
CPU:
6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3 processor
GPU:
NVIDIA Volta™ architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores
Memory:
8 GB 128-bit LPDDR4x @ 1600 MHz 51.2GB/s16 GB 128-bit LPDDR4x @ 59.7GB/s
Storage:
16 GB eMMC 5.1
Physical I/O
Display:
1x Mini DP
Ethernet:
1x RJ45 GbE (10/100/1000)
Tact Switch:
Recovery / Reset / Power / Programmable Buttons x2
USB:
1x USB3.2 Gen1 Type A
1x USB2.0 Micro B (OTG only)
Line in:
1x 3.5mm Phone Jack
Line out:
1x 3.5mm Phone Jack)
Internal Connector
Speaker out:
2x pin header (2-pin with 2.54pitch)
Mic in:
4x MEMS Microphone
Camera:
1x 15-pin FPC for MIPI CSI-II 2 Lanes
2-pin header:
1x RTC with CR2032 Battery
4-pin header:
1x Fan
7-pin header:
1x SPI for OLED
12-pin header:
1x UART (Debug only)
1x Power LED
1x Auto-power-on
1x Reset
1x Recovery
1x Power
40-pin header:
1x UART
2x I2C
1x SPI
Expansion slots:
1x M.2 2280 Key M
1x M.2 2230 Key E
Environment
Power input:
12V DC input with DC Jack
Dimension PCBA with base frame:
81(L) x 69(W) x 125(H) mm
Operating Temp:
0°C ~ 50°C
Storage Temp:
-25°C ~+80°C
Storage Humidity:
95% @ 40 °C (non-condensing
NVIDIA® JetsonXavier™ NX
CPU:
6-core NVIDIA Carmel ARM®v8.2 64-bit CPU 6MB L2 + 4MB L3 processor
GPU:
NVIDIA Volta™ architecture with 384 NVIDIA CUDA® cores and 48 Tensor cores
Memory:
8 GB 128-bit LPDDR4x @ 1600 MHz 51.2GB/s16 GB 128-bit LPDDR4x @ 59.7GB/s
Storage:
16 GB eMMC 5.1
Physical I/O
Display:
1x Mini DP
Ethernet:
1x RJ45 GbE (10/100/1000)
Tact Switch:
Recovery / Reset / Power / Programmable Buttons x2
USB:
1x USB3.2 Gen1 Type A
1x USB2.0 Micro B (OTG only)
Line in:
1x 3.5mm Phone Jack
Line out:
1x 3.5mm Phone Jack)
Internal Connector
Speaker out:
2 x pin header (2-pin with pitch 2.54mm)
Mic in:
4x MEMS Microphone
Camera:
1x 15-pin FPC for MIPI CSI-II 2 Lanes
2-pin header:
1x RTC with CR2032 Battery
4-pin header:
1x Fan
7-pin header:
1x SPI for OLED
12-pin header:
1x UART (Debug only)
1x Power LED
1x Auto-power-on
1x Reset
1x Recovery
1x Power
40-pin header:
1x UART
2x I2C
1x SPI
Expansion slots:
1x M.2 2280 Key M
1x M.2 2230 Key E
Environment
Power input:
12V DC input with DC Jack
Dimension PCBA with base frame:
81(L) x 69(W) x 125(H) mm
Operating Temp:
0°C ~ 50°C
Storage Temp:
-25°C ~+80°C
Storage Humidity:
95% @ 40 °C (non-condensing
Vision AI has been widely used with excellent results in a variety of scenarios. NLP is progressing to the next level. Apollo helps engineers in integrating audio and vision AI to build state-of-the-art edge solutions to real-world problems.
import Jetson.GPIO as GPIO
BUT1_PIN = 15
Device recovery has always been a pain for the developers. Apollo supports One-Key Recovery, making the engineering process easier and faster.
A/B (Seamless) System Updates.
Highlighted Features
The Automatic Speech Recognition application uses the NVIDIA RIVA model to transcribe spoken language (speech-to-text).
The Text-to-Speech application uses the NVIDIA RIVA model to generate speech audio based on the input text.
The Natural Language Processing (NLP) application uses the open-source NLTK model to conduct sentiment analysis on text, determining if the tone of given text is positive or negative.
The chatbot application uses the open-source Chatterbot to create chatbot instances and run NLP tasks. Such tasks include analyzing the tone of generated text and converting text to speech audio (text-to-speech).
The Speaker Verification application is the audio equivalent of facial recognition. The application detects and identifies characteristics in a person's voice with the on-board audio kit.
At work, Apollo allows employees to automate meeting minutes, facilitate access control or translate languages for multinational teams working in the same company.
Retail stores use Apollo as an automated customer service based on chatbots, to track customer emotions, or to analyze employee and customer time and attendance management.
Equipped with automatic speech recognition, Apollo is a powerful educational tool to learn a foreign language. Apollo can also be used as an interactive blackboard or chatbot for students.