Hardware Guide
The Arduino Nano 33 BLE Sense runs keyword spotting with Edge Impulse using its built-in MP34DT05 microphone. The 256 KB SRAM handles small keyword models (5-8 commands), though the 64 MHz clock limits vocabulary size compared to faster MCUs.
| Spec | Arduino Nano 33 BLE |
|---|---|
| Processor | ARM Cortex-M4F @ 64 MHz |
| SRAM | 256 KB |
| Flash | 1 MB |
| Key Features | Built-in 9-axis IMU (LSM9DS1) on Arduino Nano 33 BLE, Arduino ecosystem, Ultra-low-power BLE, Built-in microphone (Sense variant) |
| Connectivity | Bluetooth 5.0 LE, 802.15.4 (Thread/Zigbee), NFC, USB 2.0 |
| Price Range | $5 - $8 (chip), $20 - $35 (dev board) |
The Arduino Nano 33 BLE Sense's built-in microphone is the key advantage — no external hardware needed for voice input. Edge Impulse's audio classification pipeline handles MFCC extraction, training, and deployment as a single workflow. The 256 KB SRAM provides 2x the 128 KB minimum for voice models, but this is tight: a keyword model plus audio buffers and MFCC features leave under 100 KB for the application. The 64 MHz Cortex-M4F is the main constraint — MFCC computation on 1-second audio windows consumes a significant portion of the real-time budget at 64 MHz. practical vocabulary is limited — larger models exceed the RAM constraints for reliable real-time operation. Larger vocabularies require more complex models that exceed the RAM and latency budget. Edge Impulse's built-in keyword detection pipeline is well-optimized for the nRF52840, and their documentation includes Arduino Nano 33 BLE-specific tutorials. BLE enables forwarding recognized keywords to connected devices. Rating is 'Possible' because it works but with clear limitations that faster MCUs do not have.
Connect Nano 33 BLE Sense to Edge Impulse
Flash Edge Impulse firmware or use edge-impulse-daemon. The built-in MP34DT05 microphone streams audio directly to Edge Impulse Studio. Verify audio quality in the data collection view — the Sense variant's mic is adequate for keyword spotting within 1 meter.
Record keyword samples
In Edge Impulse Studio, record 50+ samples per keyword (1 second each). Include a 'noise' class with 100+ samples of background sounds. Also include a 'unknown' class with non-keyword speech. More samples improve robustness to speaker variation.
Configure audio classification pipeline
Select MFCC for audio processing and Classification (Keras) for the learning block. Edge Impulse automatically configures MFCC parameters for keyword spotting. Check the estimated latency in Edge Impulse Studio to verify it fits within the real-time budget on the Nano 33 BLE.
Deploy as Arduino library
Export from Edge Impulse as an Arduino library. Include in your sketch via #include. The library provides a continuous audio sampling loop that feeds MFCC features to the classifier. Map keyword detections to BLE characteristics or GPIO outputs.
2x the SRAM (512 KB), 4x the clock (240 MHz), and Wi-Fi. Supports larger vocabularies (20+ keywords). Requires external microphone but offers better performance and connectivity.
4x the SRAM (1 MB), 7x the clock (480 MHz). Supports 30+ keyword vocabularies. CMSIS-NN accelerated. For professional voice control applications that need high accuracy and large vocabularies.
Chain keyword detection with BLE actions on the Nano 33 BLE — design voice command workflows visually.
Get Started Free