Offline Speech Recognition
No internet required, local millisecond response; Multi-language recognition, strong noise resistance
Online/Offline LLM
Edge-Cloud Collaboration—Local voice data processing, seamless integration with LLMs
AI Noise Reduction
Adaptive noise reduction algorithm for various scenarios, making calls clearer and smoother
AI Sound Event Detection
Millisecond response, quickly identifies and distinguishes specific sound types
TTS
Converts text to clear, natural, and smooth speech in real-time without internet connection
Develop
Download
Quality and Reliability
The chip utilizes BNPU V3 and is compatible with various DNN, FTNDD, CNN, and other models.
Even in the presence of 75dB noise, the chip achieves a recognition rate of over 90%.
With high integration and simplified peripherals, the chip can be easily integrated into a complete solution with minimal external components.
The CPU operates at a maximum frequency of 240MHz, providing ample resources for development in the electronics control domain.
Available in SOP/SSOP/TSSOP/QFN packages, facilitating production design.
Users can independently change command words

Panel

Switch socket

Control system

Heated table

Curtains

Door lock

Clothes dryer

Sofa

Bed

Air conditioner

Massage chair

Fan

Tea maker

Heater

Robot cleaner

Foot bath

Air purifier

Water dispenser

Treadmill

Water purifier

Humidifier

Range hood

Refrigerator

Rice cooker

Toilet

Air fryer

Water heater

Microwave oven

Dishwasher

Washing machine

Bathroom heater

Bathroom mirror

Juicer
By providing a one-stop intelligent solution that includes development platforms, software, and hardware,
product mass production can be achieved in as fast as 15 days.




Please improve the information. Qiyintalen looks forward to working with you!