Main menu

SearchEN中文Subscribe

  • ESP32-LyraTD-MSC

    Designed for smart speakers and AI applications.
    Supports Acoustic Echo Cancellation (AEC),
    Automatic Speech Recognition (ASR),
    Wake-up Interrupt and Voice Interaction.

ESP32-LyraTD-MSC

Hardware Characteristics

ESP32-LyraTD-MSC is designed for smart speakers and AI applications. This audio development board consists of two parts: the upper board, which provides a three-microphone array, function keys and LED lights; and the lower board, which integrates ESP32-WROVER-B, a MicroSemi Digital Signal Processing (DSP) chip, and a power management module.

Wide Applicability

ESP32-LyraTD-MSC implements voice interaction and cloud-on-demand services for smart speaker applications, human-machine interaction and image recognition for AI applications, as well as interconnectivity  and real-time feedback for smart home devices.

Excellent Performance

ESP32-LyraTD-MSC facilitates the quick and easy development of dual-mode (Bluetooth + Wi-Fi) audio solutions, as it supports one-key Wi-Fi network  configuration, Acoustic Echo Cancellation (AEC), near/far-field voice wake-up, cloud platform access, voice recognition, wake-up interrupt and audio decoding.

Development Board Features
High-performance DSP chip:

supports soft decoding.
Complete audio module:

audio driver chip, earphone jack, dual speaker output, and a three-microphone array.
Power supply:

supports USB and battery.
Expansion interfaces:

I2C/SPI and I2S interfaces for data transmission, along with USB-to-UART and JTAG interfaces for debugging.
Wi-Fi + Bluetooth dual mode:

802.11 b/g/n Wi-Fi protocol, Classic Bluetooth and Bluetooth Low Energy.
Micro SD card:

for storing audio files.
ESP32-WROVER module:

Dual-core 32-bit processor with 4.5 MB of operating memory.
Development Board Features
• A lightweight, low-power and cost-effective smart audio solution.
• Access to multiple cloud platforms including DuerOS, Amazon, Tmall Genie, Turing, JD and iFLYTEK.
• HTTP live streaming, such as Internet radio and Ximalaya.
• Voice wake-up optimized with speech recognition and echo cancellation.
• Three digital MICs support far-field voice pick-up (from a distance of one to five meters).
• The dual-board design integrates an LED light strip and fully-functional buttons.
• Audio inputs over Wi-Fi, BT, DLNA, SD-Card.
• A variety of network configurations, such as Smartconfig, Bluetooth LE, and Air-kiss.
• Wi-Fi 802.11b/g/n, Classic BT and Bluetooth LE in the 2.4GHz band.
• Multiple audio formats including M4A, AAC, FLAC, OGG, OPUS, MP3, AMR.
Getting Started Guide
Read the Guide
Espressif GitHub
Visit and Download