Description
Ai-Thinker NodeMCU-VC-01-KIT Offline Speech Recognition Module
Description
- 1x Ai-Thinker NodeMCU-VC-01-KIT
- 42.2 x 35.6 (±0.2) mm
PDF File
- Ai-Thinker NodeMCU-VC-01-KIT Offline Speech Recognition Module – Manual
- Kernel: The device has a 32-bit RISC core running at 240 MHz. It supports DSP instruction set and FPU floating point operation unit
- FFT Accelerator: The device supports up to 1024-point complex FFT/IFFT operations or 2048-point real FFT/IFFT operations
- Unisound Customized Speech Algorithm Operator: The device is equipped with this feature
- Storage: The device has built-in 242 KB high-speed SRAM and 2 MB FLASH
- Audio Input and Output: The device supports flexible configuration with 1.8/2.8/3.3V IO. It has 1 analog Mic input with SNR≥94db. It also supports dual-channel DAC output and both Chinese and English voice commands
- Power Supply and Clock: The device supports 5V power input. It has built-in 5V to 3.3V and 3.3V to 1.2V LDO to power the chip. It uses RC 12 MHz clock source and PLL locked loop clock source. It also has built-in POR (Power on Reset), low voltage detection, and watchdog
- Peripheral: All GPIOs can be configured as external interrupt input and wake-up source. The device has one full-duplex UART with a maximum rate of 3 Mbps. It also supports I2C DAC PWM and multiple interfaces
- SDK: The device provides a complete RTOS SDK. It supports fast and convenient UART, I2C, and other control protocol development
- Working temperature: -40 to 85 ℃
- Storage environment: -40 to 125 ℃, < 90%RH
- Power supply: Supply voltage 5 V, current greater than 500 mA
- Interfaces: UART/I2C/PWM/DAC/GPIO
- IO: 5 GPIOs
- UART rate: UART1 default 115200 bps, UART0(IOB8) default 57600
- Flash: 2 MB (built-in)
- Support language: English and Chinese
