Picovoice Platform
Go Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• BeagleBone
• NVIDIA Jetson Nano
• Raspberry Pi (2, 3, 4)

Requirements

• Picovoice Account & AccessKey
• Go 1.16+
• Windows only: a gcc compiler like Mingw in $PATH

Picovoice Account & AccessKey

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

Quick Start

Setup

1. Download and install Go language .

2. Install the Picovoice Go Package using the Go CLI:

go get github.com/Picovoice/picovoice/sdk/go/v2

Usage

Create an instance of Picovoice using a Porcupine keyword file (.ppn), and a Rhino context file (.rhn):

. "github.com/Picovoice/picovoice/sdk/go/v2"
. "github.com/Picovoice/rhino/binding/go/v2"

wakeWordCallback := func(){
    // wake word detected
}

inferenceCallback := func(inference RhinoInference){
    if inference.IsUnderstood {
            intent := inference.Intent
            slots := inference.Slots
        // take action based on inferred intent and slot values
    } else {
        // handle unsupported commands
    }
}

picovoice := NewPicovoice(
    "${ACCESS_KEY}",
    "${KEYWORD_FILE_PATH}", 
    wakeWordCallback, 
    "${CONTEXT_FILE_PATH}", 
    inferenceCallback)
err := picovoice.Init()

Pass in frames of audio to the .Process function:

func getNextAudioFrame() []int16 { 
   // ..
}

for {
   audioFrame := getNextAudioFrame()
   err := picovoice.Process(audio_frame)
}

Release resources explicitly when done with Picovoice:

picovoice.Delete()

Custom Wake Words & Contexts

Create custom wake word and context files using the Picovoice Console . Download the custom models (.ppn and .rhn) and pass them into the NewPicovoice constructor.

Non-English Languages

Use the corresponding model file (.pv) to process non-English wake words and contexts. The model files for all supported languages are available on the Porcupine GitHub repository and the Rhino GitHub repository .

Pass in model files using the PorcupineModelPath and the RhinoModelPath parameters to change the language:

picovoice := NewPicovoice(
    "${ACCESS_KEY}",
    "${KEYWORD_FILE_PATH}", 
    wakeWordCallback, 
    "${CONTEXT_FILE_PATH}", 
    inferenceCallback)
picovoice.PorcupineModelPath = "${PORCUPINE_MODEL_FILE_PATH}"
picovoice.RhinoModelPath = "${RHINO_MODEL_FILE_PATH}"
err := picovoice.Init()

Demo

For the Picovoice Go SDK, we offer demo applications that demonstrate how to use the Picovoice Platform on real-time audio streams (i.e. microphone input) and audio files.

Setup

Clone the Picovoice GitHub Repository :

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

Usage

Use the -h flag to see the usage options for the demo:

cd picovoice/demo/go
go run micdemo/picovoice_mic_demo.go -h

Ensure you have a working microphone connected to your system and run the following command to make inferences based on the given keyword and context files:

go run micdemo/rhino_mic_demo.go -access_key "${ACCESS_KEY}" \ 
-keyword_path "${KEYWORD_FILE_PATH}" \
-context_path "${CONTEXT_FILE_PATH}"

For more information on our Picovoice demos for Go, head over to our GitHub repository .

Resources