Picovoice Platform
Python Quick Start

Platforms

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

Requirements

• Picovoice Account & AccessKey
• Python 3
• PIP

Picovoice Account & AccessKey

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

Quick Start

Setup

1. Install Python 3 .

2. Install the picovoice Python package using PIP:

pip3 install picovoice

Usage

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

from picovoice import Picovoice

def wake_word_callback():
    # wake word detected
    pass

def inference_callback(inference):
   if inference.is_understood:
      intent = inference.intent
      slots = inference.slots
      # take action based on intent and slot values
   else:
      # unsupported command
      pass

handle = Picovoice(
     access_key=${ACCESS_KEY},
     keyword_path=${KEYWORD_FILE_PATH},
     wake_word_callback=wake_word_callback,
     context_path=${CONTEXT_FILE_PATH},
     inference_callback=inference_callback)

Pass in frames of audio to the .process function:

def get_next_audio_frame():
    pass

while True:
    audio_frame = get_next_audio_frame()
    handle.process(audio_frame)

Release resources explicitly when done with Picovoice:

handle.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 Picovoice constructor.

handle = Picovoice(
     access_key=${ACCESS_KEY},
     keyword_path=${KEYWORD_FILE_PATH},
     wake_word_callback=wake_word_callback,
     context_path=${CONTEXT_FILE_PATH},
     inference_callback=inference_callback)

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 porcupine_model_path and the rhino_model_path parameters to change the language:

handle = Picovoice(
    access_key="${ACCESS_KEY}",
    keyword_path="${KEYWORD_FILE_PATH}", 
    wake_word_callback=wake_word_callback, 
    context_path="${CONTEXT_FILE_PATH}", 
    inference_callback=inference_callback,
    porcupine_model_path="${PORCUPINE_MODEL_FILE_PATH}",
    rhino_model_path="${RHINO_MODEL_FILE_PATH}")

Demo

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

Setup

Install the picovoicedemo Python package using PIP:

pip3 install picovoicedemo

This package installs command-line utilities for the Picovoice Python demos.

Usage

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

picovoice_demo_mic --help

Ensure you have a working microphone connected to your system and run the following command to infer intent from spoken commands:

picovoice_demo_mic --access_key ${ACCESS_KEY} --keyword_path ${KEYWORD_FILE_PATH} --context_path ${CONTEXT_FILE_PATH}

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

Resources