Genai With Python: Give Your AI a Personality and Speak With ”Her”

Author(s): Mauro Di Pietro

Originally published on Towards AI.

LLM & Speech Recognition — Build a voice assistant ChatBot on your laptop with Ollama
Image by author

In this article, I will show how to build an AI with a specific personality and how to have voice conversations with it on your laptop without GPU.

generated with Luma’s DreamMachine

Chatbots are software applications used to conduct automatic chat conversations via text or text-to-speech, imitating the interaction with a human agent. The first one was ELIZA (1966), which used pattern matching and substitution methodology to simulate a textual conversation (it couldn’t either listen or speak).

When a chatbot can perform tasks other than conversation, it’s a “voice assistant” that responds to voice commands leveraging NLP and Speech Recognition (i.e., Siri or Alexa). Currently, the most advanced on the market is probably the new Apple’s AI which empowers Siri with onscreen awareness (it can take action with things on your screen) and Large Language models (LLMs).

In this tutorial, I’m going to create a ChatGPT-like AI, giving the chatbot a personality, and we will speak with it using Speech Recognition. I will present some useful Python code that can be easily applied in other similar cases (just copy, paste, run) and walk through every line of code with comments so that you can replicate this example (link to the full code… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI