WTK6900FC Snore Recognition Chip
AI‑Powered Snore Detection with Hardware Output, UART Protocol & 95dB SNR Audio
The WTK6900FC Snore Recognition Chip is an AI‑powered snore recognition chip designed specifically for smart sleep health applications. Powered by a 220MHz CPU with a dedicated BNPU V3 neural accelerator, it delivers ≥95% recognition accuracy with ≤300ms response delay. The chip features a hardware signal output (Pin14) for simple hardware triggering, a UART protocol for precise data transmission, and speaker prompt control for user feedback. With 95dB SNR audio codec and ultra‑low power consumption, it is the ideal solution for smart pillows, sleep monitors, and health wearables.
- ≥95% accuracy – deep learning‑based snore detection
- ≤300ms delay – real‑time response
- Pin14 hardware output – 12s high‑level signal
- UART protocol – A5FA008120FB frame output
- Speaker control – customizable voice prompts
WTK6900FC Snore Recognition Chip Key Features
Snore Recognition Specifications
| Parameter | Value / Description |
|---|---|
| Recognition Technology | DNN‑HMM deep neural network |
| Recognition Accuracy | ≥ 95% (typical bedroom environment) |
| Response Delay | ≤ 300 ms |
| Detection Range | 30 – 80 dB |
| Noise Immunity | Filters background noise below 60dB |
| Hardware Output | Pin14 – 12s high‑level signal on detection |
| UART Protocol | 9600 baud, frame: A5FA008120FB |
| Sensitivity Modes | High / Medium (default) / Low |
| Speaker Prompt Control | Enable: A5FA00E0100AEFB / Disable: A5FA00E0000ADFB |
| Training Data | 10+ million snore samples |
Core Functions
Hardware Output (Pin14)
- Outputs a 12‑second high‑level signal on snore detection
- Drive capacity: 20mA (external amplification for higher loads)
- Ideal for vibration modules, LED indicators, and simple hardware triggers
UART Protocol Output
- Fixed protocol frame:
A5FA008120FB@ 9600 baud - Enables precise snore detection for complex logic control
- Supports snore count statistics and sleep quality analysis
Speaker Prompt Control
- Enable:
A5FA00E0100AEFB - Disable:
A5FA00E0000ADFB - Customizable prompt sounds for different application scenarios
Sensitivity Modes
- High: For quiet environments, light snoring detection
- Medium (Default): Balanced performance
- Low: For noisy environments to avoid false triggers
- Adjustable via custom protocol
Audio Codec Specifications
| Parameter | Value / Condition |
|---|---|
| ADC Resolution | 16‑bit |
| ADC SNR | ≥ 95 dB |
| DAC Resolution | 16‑bit |
| DAC SNR | ≥ 95 dB |
| Audio Interfaces | 1×IIS (Master/Slave), 1×PDM (2‑channel) |
| Microphone Input | Differential (MICPR / MICPL) for ECM |
| Recommended MIC | JMO-627BA283R-10TC38 (Sensitivity: -28dB, S/N: 70dB) |
Technical Specifications
| Parameter | Value / Condition |
|---|---|
| Package | SSOP24 (8.65×6.00mm) |
| CPU Frequency | Up to 220 MHz |
| Flash Memory | 2MB (WTK6900FC) / 32MB (WTK6900FC3) |
| SRAM | 640 KB |
| eFuse | 512‑bit for encryption |
| PMU Input Voltage | 3.6V – 5.5V |
| VOUT (IO / Codec) | 3.3V (2.97–3.63V) |
| VREG (Core) | 1.1V (0.99–1.22V) |
| GPIO | 10 high‑speed (20MHz), 7×5V‑tolerant |
| UART | 3×, up to 3Mbps, 5V‑tolerant |
| I2C | 1× |
| Timers | 4×32‑bit timers, 2×watchdog |
| PWM Channels | 6× |
| ADC | 1×12‑bit SAR ADC |
| Snore Recognition Power | 145 mW (typical) |
| Operating Temperature | ‑40°C ~ +85°C |
| Storage Temperature | ‑65°C ~ +150°C |
Key Pin Functions (SSOP24)
| Pin | Name | Function |
|---|---|---|
| 1 | AVDD | Analog power (4.7µF cap to ground) |
| 2 | VCC | Power input (3.6–5.5V) |
| 3 | VOUT | 3.3V LDO output (4.7µF cap) |
| 4 | VREG | Core voltage (4.7µF cap) |
| 9 | P02 | UART1_RX (communication input) |
| 10 | P03 | UART1_TX (communication output) |
| 14 | TX / DAT | Snore signal output (12s high) + UART1_RX / Programming |
| 16 | BUSY | IO port / Busy signal |
| 17 | DAC | DAC audio output (speaker prompt) |
| 20 | MICPR | Microphone input (−) |
| 21 | MICPL | Microphone input (+) |
| 22 | MICLDO | Microphone power supply (4.7µF cap) |
| 23 | VCM | Common mode voltage reference |
| 24 | AGND | Analog ground |
Application Scenarios
Smart Sleep Health Devices
Smart Home Systems
Health & Medical Devices
Automotive & Consumer Electronics
Why Choose WTK6900FC Snore Recognition Chip
Frequently Asked Questions
What is the WTK6900FC snore recognition chip?
WTK6900FC Snore Recognition Chip is an AI-powered snore recognition chip with a 220MHz CPU, BNPU V3 neural accelerator, 95dB SNR audio codec, and dedicated hardware signal output for snore detection. It supports 3 sensitivity modes and UART protocol for data transmission.
How does the hardware signal output work?
When snoring is detected and confirmed, Pin14 outputs a 12-second high-level signal. External devices can use this pin for simple hardware triggering such as vibration modules or light adjustments.
What is the serial protocol for snore detection?
WTK6900FC Snore Recognition Chip outputs a fixed protocol frame A5FA008120FB via UART at 9600 baud. External MCUs can read this frame to accurately determine snore detection events.
Can the speaker prompt be controlled?
Yes. Send A5FA00E0000ADFB to disable the speaker prompt, and A5FA00E0100AEFB to enable it. The prompt sound can be customized for different applications.
What is the recognition accuracy?
In typical bedroom environments, the snore recognition accuracy is ≥95%, with strong anti-interference against background noise below 60dB.
What is the response delay?
The delay from snore detection to signal output is ≤300ms, enabling real-time feedback for interactive applications.
What are the sensitivity modes?
WTK6900FC Snore Recognition Chip supports three sensitivity modes: High sensitivity (for quiet environments, light snoring), Medium sensitivity (default, balanced), and Low sensitivity (for noisy environments to avoid false triggers).
What microphone is recommended?
The recommended microphone is JMO-627BA283R-10TC38, an electret condenser microphone with -28dB sensitivity and 70dB S/N ratio.
What is the power consumption during snore detection?
Snore recognition mode power consumption is as low as 145mW (typical), making it suitable for wearable devices and long-battery-life health products.
What are the typical applications?
Smart pillows, sleep monitors, health wristbands, smart beds, smart home systems, elderly health监护 devices, automotive driver fatigue monitoring, and smart headphones.
Important: For optimal snore recognition performance, use the recommended microphone (JMO-627BA283R-10TC38). Pin14 outputs a 12s high-level signal with 20mA drive capability – use external amplification for higher loads. The chip operates at 3.6–5.5V input. Ensure proper PCB layout with analog/digital ground separation. The speaker prompt and sensitivity mode can be customized via protocol. For custom firmware or command set modifications, contact Waytronic support.
