Cobra VAD — Microcontroller Quick Start

Platforms

• Arm Cortex-M4

Requirements

• C99-compatible compiler

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Cobra VAD for MCU is currently in Beta and available for evaluation for 30 minutes per device, (i.e., user). If you are working on a commercial project or require extended access, please contact Picovoice with your project details.

Quick Start

Setup

1. Clone the repository:

git clone --recurse-submodules https://github.com/Picovoice/cobra.git

Usage

1. Include the public header files (picovoice.h and pv_cobra.h).
2. Link the project to an appropriate precompiled library for the target platform and load it.
3. Construct the Cobra Voice Activity Detection object:

#define MEMORY_BUFFER_SIZE ${MEMORY_BUFFER_SIZE}
static const char* ACCESS_KEY = "${ACCESS_KEY}";

uint8_t memory_buffer[MEMORY_BUFFER_SIZE] __attribute__((aligned(16)));

pv_cobra_t *cobra;

const pv_status_t status = pv_cobra_init(ACCESS_KEY, MEMORY_BUFFER_SIZE, memory_buffer, &cobra);

if (status != PV_STATUS_SUCCESS) {
    // error handling logic
}

4. Pass in audio to the pv_cobra_process function:

extern const int16_t *get_next_audio_frame(void);

while (true) {
    const int16_t *pcm = get_next_audio_frame();

    float is_voiced = 0.f;
    const pv_status_t status = pv_cobra_process(cobra, pcm, &is_voiced);
    if (status != PV_STATUS_SUCCESS) {
        // error handling logic
    }
}

5. Release resources explicitly when done with Cobra Voice Activity Detection:

pv_cobra_delete(cobra);

Demo

For the Cobra Voice Activity Detection SDK, we offer demo applications that demonstrate how to use the VAD engine on real-time audio streams (i.e. microphone input) on microcontrollers.

Setup

1. Clone the Cobra Voice Activity Detection repository from GitHub using HTTPS:

git clone --recurse-submodules https://github.com/Picovoice/cobra.git

Usage

• Arduino Nano 33 BLE Sense (Arm Cortex-M4)
• STM32F411E-DISCO (Arm Cortex-M4)

Resources