Echo-voice

Minimal setup for speech-to-text transcription and text-to-speech generation.

Requirements

• Python 3.9 (pynput requires ≤3.9, other libraries require ≥3.8)
• ffmpeg (see installation instructions below)
• A Python package manager like uv.

Instructions

1. Install command-line tool ffmpeg, required for speech-to-text transcription, on your system, which is available from most package managers:

   # 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
   

2. Install Python dependencies:

   uv sync

3. Run the application:

   uv run python main.py

4. Controls:

   • Press Space to start/stop recording
   • Press ESC to exit the application

Tech Stack

• Python - Core language
• OpenAI Whisper API - Speech-to-text transcription
• PyAudio - Audio recording from microphone
• pynput - Keyboard event handling
• bark - Text-to-speech generation
• uv - Python package management