trans-vox

A simple Speech-to-Text (STT) and Text-to-Speech (TTS) tool.

Setup

# Create virtual environment
python -m venv venv
source venv/bin/activate

Install Dependencies

Speech-to-Text (STT)

pip install SpeechRecognition
pip install openai-whisper

Text-to-Speech (TTS)

pip install gTTS
pip install piper-tts

Download Piper voice model (example: en_US-lessac-medium):

python3 -m piper.download_voices en_US-lessac-medium

---

Usage

Speech-to-Text (STT)

python stt.py -i input.wav -o output/ -m whisper

Arguments:

• -i, --input : Path to the input audio file (required)
• -o, --output: Path to the output directory (default: output)
• -m, --model : STT engine to use: whisper or google (default: whisper)

---

Text-to-Speech (TTS)

python tts.py -i input.txt -o output/ -m piper

Arguments:

• -i, --input : Path to the input text file (required)
• -o, --output: Path to the output directory (default: output)
• -m, --model : TTS engine to use:
  • gtts → outputs MP3 (default)
  • piper → outputs WAV