api.ai: Python SDK for API.AI

Overview

The API.AI Python SDK makes it easy to integrate speech recognition with API.AI natural language processing API. API.AI allows using voice commands and integration with dialog scenarios defined for a particular agent in API.AI.

Prerequsites

Create an API.AI account.

Running examples

1. Find examples from 'examples' path.
2. Insert API key & subscription.

>>> CLIENT_ACCESS_TOKEN = '<YOUR_CLIENT_ACCESS_TOKEN>'
>>> SUBSCRIPTION_KEY = '<YOUR_SUBSCRIPTION_KEY>'
...

Features

• Speech Recognition.
• Voice Activity Detection.
• Natural Language Processing.

Installation

To install apiai, simply:

$ pip install apiai

or install it from repo:

$ pip install https://github.com/api-ai/api-ai-python.git

You might run into problems because some dependencies in your python environment are missing. You need to install numpy (which is available in alomost all package managers) and scipy. For running the examples you also need python audio.

In ubunutu the following will do the job:

$ apt-get install python-pyaudio python-numpy python-scipy python-matplotlib ipython ipython-notebook python-pandas python-sympy python-nose python-pip
$ pip install apiai

Documentation

Documentation is available at http://api.ai.