A simple yet powerful voice assistant that listens to your speech, converts it to text, and responds with synthesized speech. Built with Python using gTTS and SpeechRecognition.
- Speech‑to‑Text (STT) – Converts your spoken words to text using Google's Speech Recognition API.
- Text‑to‑Speech (TTS) – Responds with natural‑sounding speech using Google Text‑to‑Speech (
gTTS). - Basic Commands – Understands simple commands like greetings, time queries, and farewells.
- Extensible – Easily add new commands and integrate with other APIs or LLMs.
- Cross‑Platform – Works on Windows, macOS, and Linux.
- Python 3.12 or higher
- A working microphone
- Internet connection (for Google STT and TTS)
- uv – a fast Python package installer and virtual environment manager (recommended).
If you don't haveuv, install it with:# On macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh # On Windows (PowerShell) powershell -c "irm https://astral.sh/uv/install.ps1 | iex" uv pip install -r requirements.txt
- Clone the repository:
git clone https://github.com/mustapha-devstack/voice-stt-tts.git cd voice-stt-tts