Piper is a fantastic tool for providing very realistic sounding TTS while also being efficient and fast. There are some publicly available pre-trained models, but if you’re here, that means you want to create your own voice. This guide aims to walk you through the steps.

The tool/function calling equivalent for Ollama, looking quite similar to Gemini

The offline Model library for Python

A Python class that encapsulates a Selenium-based web scrapper that outcomes a list of products and its prices from a given department URL.

Similar to the previous link, but apparently there is a new way to do so in the newer 2.x versions that simplifies all internally.

Example of functions in Python to make Google Gemini to give weather forecast for a location during a chat

How to use functions from within the Chat session besides the Generate Content, so chat history and more is self managed. In Python

Stack Overflow. How to use Python's Multiprocessing Managers to instantiate a Proxy class to access to the methods of the child process. You can pass params, so why to bother with all the hassle of the Queues?

Several approaches in Stack Overflow to colorize the logs in Python.

This document explains how to set up and use live microphone input with the Vosk speech recognition system. It covers capturing real-time audio from microphones in both Python and Node.js, passing the audio data to the Vosk recognition engine, and processing the results