WAV leverages cutting-edge AI technologies to enhance the coding experience by allowing developers to generate code through voice commands. Utilizing OpenAI's Whisper for speech-to-text transcription and GPT models for intelligent code generation, WAV aims to streamline the development process, making it more efficient and accessible.

Features WAV offers a unique set of features designed to improve productivity and reduce the barrier between ideation and implementation:

Voice-to-Code Translation: Convert spoken language into syntactically correct code snippets across various programming languages.

Context-Aware Suggestions: Generate code based on the context of the current file and the developer's spoken instructions.

Seamless Integration: Works directly within VSCode, providing an intuitive and unobtrusive user experience.

on Ubuntu or Debian

sudo apt update && sudo apt install ffmpeg

on Arch Linux

sudo pacman -S ffmpeg

on MacOS using Homebrew (https://brew.sh/)

brew install ffmpeg

on Windows using Chocolatey (https://chocolatey.org/)

choco install ffmpeg

on Windows using Scoop (https://scoop.sh/)

scoop install ffmpeg

Usage:

CTRL+SHIFT+A -> Start Recording CTRL+SHIFT+S -> Stop Recording, begin transcription process and generation.

Requirements To use WAV, ensure you have the following:

Tested on VSCode 1.86.2, should work ^1.86.0. Python 3.7 or higher, required for running the transcription and AI models. OpenAI API keys for accessing Whisper and GPT models.

IMPORTANT: This version of WAV is in alpha and is still being tested under specific development environments.