ESP32-AIVoice-Z01 AI Large Model(LLM) Development Kit ChatGPT-4o/Llama 3 Voice Assistant Chatbot, Multi-model support

3,599.00 excl GST

2 in stock

ESP32-AIVoice-Z01 AI voice development kit with ESP32-S3, dual-mic array, Wi-Fi/BLE, noise cancellation, 2.5W audio amp and LLM voice chatbot support.

SKU: ro-856 Category:

ESP32-AIVoice-Z01 is a high-cost-performance AI audio development kit designed by YUMOU Intelligent, which can be used to quickly implement AI voice applications, embedded AI learning, and rapid development and verification of AI voice products. It is equipped with dual high-sensitivity high signal-to-noise ratio digital microphones, DVP universal camera interface, TF card slot, RGB colorful lights, 3.7V lithium battery interface, battery voltage measuring IC, and other peripherals.

The ESP32-S3R8/ESP32-S3R2 chips it uses integrate low-power WiFi and BLE5.0, with external 16MB Flash and 8MB/2MB PSRAM, built-in hardware encryption accelerators, random number generators, HMAC, and digital signature modules. Thus, it meets users’ development needs in low-cost, low-power AI large model toys, IoT, mobile devices, outdoor monitoring, smart homes, and other fields.


Features


  • Onboard ESP32-S3 Dual-Core High-Performance Embedded Controller with a main frequency of 240MHz, equipped with 8M PSRAM and an external 16MB Flash memory, capable of effectively handling various voice application scenarios.
  • Integrated 2.4GHz Wi-Fi and Low Power Bluetooth (BLE) Dual-Mode Wireless Communication, boasting superior radio frequency performance.
  • Onboard Dual Digital Microphone Array, capable of effectively implementing various audio processing algorithms, significantly enhancing audio quality and voice recognition accuracy.
  • Onboard Ultra-High Sensitivity (S) and Signal-to-Noise Ratio (SNR) Dual Digital Microphones, supporting high-quality voice processing.
  • Support for Espressif WakeNet Voice Wake-Up Framework, supporting dual-channel voice wake-up, improving wake-up rate and distance.
  • Onboard Maximum 2.5W Power Amplifier, capable of connecting to external speakers, led out through 1.25mm*2PIN terminals.
  • Support for Dual-Microphone Noise Reduction Algorithms, enabling AI voice chat interruption features.
  • Support for VAD Algorithm, capable of detecting current voice activity status, enabling continuous dialogue features in AI voice chat.
  • Support for AEC Algorithm, effectively removing echo during voice calls, achieving echo cancellation.
  • Seamless Integration with AiLinker Open-Source Backend Service Framework, for rapid AI large model service docking. (Currently supports OpenAI, ZhiPu QingYan, TongYi QianWen, DouBao, and other large model services, with continuous updates).
  • Seamless Integration with AiLinker Open-Source Backend Service Framework, for rapid online voice recognition service and online text-to-speech service docking. (It currently supports Volcano Engine, iFlytek Voice Services, etc., with continuous updates.)
  • Easy Implementation of AI Voice Chat with AiLinker Open-Source Framework, supporting custom large model roles, custom interaction timbres, and creating personal exclusive AI voice assistants.
  • Easy Implementation of AI Peripheral Control with AiLinker Open-Source Framework, for creating AI control terminals, AI mobile robots, smart home managers, and other applications.
  • Onboard SPI Screen Interface, led out through 1.25mm*8PIN terminals.
  • Comprehensive Support Documentation and Basic Software SDK Provided.

Package Contains


  • AI_VOICE_Z01 main board × 1

  • Transparent acrylic upper case × 1

  • Transparent acrylic lower case × 1

  • Screw package × 1

  • 4Ω 2-watt 4030 speaker × 1

  • FPC antenna × 1

  • USB Type-C cable (about 1m) × 1

  • Screwdriver × 1

 

 

Applications


Meeting users’ development needs in low-cost, low-power, AI large model toys, IoT, mobile devices, outdoor monitoring, smart home, and other fields.

 

Specification


 

Feature Specification
WiFi Standard 802.11b/g/n
Bluetooth Standard Low Power Bluetooth 5.0 (BLE)
Processor Xtensa LX7 Dual-Core Processor @240MHz
SRAM 512KB + 8MB
Flash Memory 384KB + 16MB
Input Voltage 3.3V ~ 5V
Operating Voltage 3.3V
Charging Current 555mA @5V
Power Consumption <10mA @5V (Deep Sleep)
Amplifier 4 Ohm 2.5W
Microphone Dual digital silicon microphones, SNR 65dB
External Microphone Interface Supports dual 1.25mm*4PIN external connection
External Storage Supports TF card
Screen Interface Supports SPI interface screen
Camera Interface DVP interface, supports 30w to 500w pixel CMOS Sensor (Voice version not supported)
Product Dimensions 77mm × 36mm × 32mm
Operating Temperature -10℃ ~ 60℃
ESD Protection Air ±8kV, Contact ±4kV
Ingress Protection Not waterproof


Detailed Descriptions


 
       
Quick Start Click here Github EN

⚠ NOTE:
Images are for representation only. Actual product appearance may vary slightly. This product does not include a battery and it must be purchased separately.

❗ IMPORTANT:
Due to the nature of this product, we do not offer technical support for this product. Please refer to the documentation for setup and usage.


Important Product Disclaimer

Please note that the product information provided on our website may not be entirely accurate as it is collected from various sources on the web. While we strive to provide the most up-to-date information possible, we cannot guarantee its accuracy. We recommend that you always read the product labels, warnings, and directions before using any product. Product images are shown for illustrative purposes only and may differ from the actual product.

Only logged in customers who have purchased this product may leave a review.

Reviews

There are no reviews yet.

Main Menu

ESP32-AIVoice-Z01 AI Large Model(LLM) Development Kit ChatGPT-4o/Llama 3 Voice Assistant Chatbot, Multi-model support

ESP32-AIVoice-Z01 AI Large Model(LLM) Development Kit ChatGPT-4o/Llama 3 Voice Assistant Chatbot, Multi-model support

3,599.00 excl GST

Add to cart
0