YT-Voice-Assistant

Project Summary: Developed a basic proyect Python-based system for real-time voice-to-text transcription and YouTube content search. Implemented precise voice recognition and advanced search using the YouTube API. Optimized accuracy and relevance through testing, receiving positive client feedback and enhancing my skills in algorithms and API integration. Note: Made in PyCharm on W11.

Features

• Real-Time Transcription: Converts voice input to text with high accuracy.
• YouTube Content Search: Uses YouTube API for advanced search based on transcribed voice input.
• Download Options: Supports video/audio downloads using yt-dlp.

Installation

To run this project, you need to install the following dependencies:

pip install pyaudio
pip install SpeechRecognition
pip install yt_dlp

Usage

1. Clone the repository: (opcional)

git clone https://github.com/ErmJJ/YT-Voice-Assistant.git
cd YT-Voice-Assistant

2. Install using python terminal:

pip install pyaudio
pip install SpeechRecognition
pip install yt_dlp

3. Run the application:

py main.py

4. Or just download the python file en execute in visual studio code, idle or terminal

Requirements

• Python 3.8 or higher
• PyAudio
• SpeechRecognition
• yt-dlp

Technologies Used

• Python: Main programming language
• PyAudio: For capturing audio input
• SpeechRecognition: For real-time voice transcription
• YouTube API: For content search
• yt-dlp: For downloading video/audio content

License

This project is licensed under the MIT License.

Author

Developed by Julián Hernández (ErmJJ)