VC-01 is a low-cost pure offline speech recognition module, Ai-Thinker Technology. The module uses the voice chip US516P6 launched by Uni sound, and continuously optimizes and innovates algorithms in speech recognition technology. The offline recognition algorithm and chip architecture are deeply integrated to provide customers with ultra-low-cost offline speech recognition solutions. It can be widely and quickly applied to smart homes, all kinds of smart small household appliances, 86 boxes, toys, lamps, and other products that need voice control. The US516P6 chip uses a 32-bit RSIC architecture core and incorporates a DSP instruction set specifically for signal processing and speech recognition, an FPU arithmetic unit that supports floating-point operations, and an FFT accelerator. VC-01 supports offline identification of 150 local instructions, an RTOS lightweight system, rich peripheral interfaces, and simple and friendly custom tools.

Features:-

• 32bit RISC core, running at 240MHz
• Support DSP instruction set and FPU floating-point operation Unit
• FFT Accelerator: Support 1024-point complex FFT/IFFT operations, or 2048-point real FFT/IFFT operations
• Uni sound customized speech algorithm operator
• RC 12MHz clock source and PLL locked loop clock source
• Built-in POR (Power on Reset), low voltage detection and watchdog

Specifications:-

• Model: VC-01
• Package: SMD-24
• Size 25.5 x 24 x 3.2 (± 0. 2) mm
• Working temperature: -40 ℃ ~ 85 ℃
• Storage environment: -40 ℃ ~ 125 ℃, <90% RH
• Supply Voltage: 3.6 V-5 V, Supply Current> 500mA
• Interfaces: UART/I2C/PWM/SPI/GPIO
• IO: 12
• UART Rate: Default 115200 bps
• SPI Flash: 2MB (built-in)

Package Includes:-

1 x Ai-Thinker VC-01 module