Edgi-Talk is a machine learning platform/development kit powered by Infineon PSOC Edge E84 Arm Cortex-M55/M33 SoC with Arm Helium, Arm Ethos-U55 micro NPU, and ultra-low-power NNLite neural network accelerators, all of which enable AI/ML processing at various power/performance levels.
The development kit also comes with 128MB PSRAM, 128MB QSPI Flash, a 4.3-inch capacitive touchscreen display, two digital microphones, speakers, WiFi 6 and Bluetooth LE 6.0 wireless connectivity, motion and environmental sensors, as well as a 40-pin Raspberry Pi header and two PMOD connectors for expansion.
Edgi-Talk specifications:
- SoC – Infineon PSOC Edge E84
- CPU
- Arm Cortex-M55 @ 400 MHz, FPU, MPU, Arm Helium support, 256KB i-TCM, 256KB D-TCM, and 5MB SRAM
- Arm Cortex-M33 @ 200MHz, 1MB SRAM, 64KB ROM
- GPU – Low power 2.5D GPU
- NPU – Dual Architecture Arm Ethos-U55 NPU + NNLITE NPU
- CPU
- System memory – 128 MB PSRAM
- storage
- 128MB QSPI Flash
- microSD card slot
- Display – 4.3-inch MIPI-DSI high-resolution capacitive touchscreen
- audio
- 2x digital microphone
- 1W amplifier for built-in speaker
- USB – USB High Speed Type-C Port
- Wireless – Dual-band Wi-Fi 6 and BLE 6.0 via Infineon AIROC CYW55512
- sensor
- AHT20 Temperature and Humidity Sensor
- LSM6DS3TR-C 6-axis inertial measurement unit
- expansion
- 40-pin Raspberry Pi compatible GPIO header with UART, SPI, I2C…
- 2x PMOD connectors
- Debugging – USB-C port, DAP/trace via 6-pin SWD pad
- power supply
- 5V via USB Type-C port
- 2-pin battery connector for standard 500 mAh 502540 LiPo battery (sold separately)
- Dimensions – 115 x 73 x 20 mm
This development board is supported by RT-Thread RTOS and comes pre-bundled with the XiaoZhi AI large language model, allowing users to build voice assistant prototypes, create smart sensor hubs, and develop smart human-computer interfaces (HMIs).
There is an RT-Thread Board Support Package (BSP) on GitHub, which also provides code samples (in C) for all the features of the board, as well as basic documentation to get started with the RT-Thread Studio IDE. A video demo of this platform is embedded at the end of this post.
RT-Thread launched Edgi-Talk on Crowd Supply with a fundraising goal of $13,900. This equates to 100 development kits for $139. Each includes a development board, a custom enclosure, an integrated touch display, speakers, two microphones for local interaction with the preinstalled Xiao Zhi large language model, and one USB Type-C cable. Shipping is free to the US, but $14 will be added to other locations. Deliveries are scheduled to start at the end of February 2026.
Jean-Luc started CNX Software as a part-time job in 2010, then quit his job as a software engineering manager and began writing daily news and reviews full-time in late 2011.
Support CNX Software! Donate in crypto, become a patron on Patreon, or buy on Amazon or Aliexpress. We also use affiliate links in our articles and receive a commission if you click the link and purchase a product.
