Voice2Voice

An intelligent audio studio for speech-to-text and text-to-speech processing, with full support for the Persian language.

---

Features

Section	Description	Type
STT — Speech to Text	Convert audio files to text using Whisper or Vosk	Local
Online STT	Convert speech to text using Gemini	Online
TTS — Text to Speech	Convert Persian text to speech with 5 distinct voices	Local
Podcast	Generate a two-person dialogue with two different voices	Local
Tone Lab	Generate speech with a variety of tones	Local
Voice Cloning	Clone a voice using Gemini	Online

Local TTS Voices (Piper TTS)

ID	Persian Name
amir	Amir
ganji	Ganji
gyro	Gyro
reza	Reza Ebrahim
mana	Mana

---

Prerequisites

• Python 3.9+
• Node.js 18+
• FFmpeg (for audio processing)

---

Setup

1. Get the project

git clone <your-repo-url>
cd "Voice2Voice"

2. Backend

cd BackEnd

# Setup venv
python -m venv venv
\venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Automatically download models
python download_models.py

Create a .env file (for online STT and voice cloning):

GEMINI_API_KEY=your_api_key_here

To get a Gemini API key: https://aistudio.google.com/app/apikey

Run the server:

uvicorn api_whisper_vosk:app --host 0.0.0.0 --port 8000

3. Frontend

cd Frontend
npm install
npm run dev

Then open your browser at http://localhost:5173.

---

Project Structure

Voice2Voice/
├── BackEnd/
│   ├── api_whisper_vosk.py   # FastAPI — Local STT + TTS
│   ├── download_models.py    # Script for automatic model downloads
│   ├── requirements.txt      # Python dependencies
│   ├── .env                  # Gemini API key
│   └── models/
│       ├── tts/              # Piper TTS models (5 voices)
│       │   ├── amir/
│       │   ├── ganji/
│       │   ├── gyro/
│       │   ├── reza/
│       │   └── mana/
│       └── vosk-model-fa-0.42/  # Persian Vosk model
├── Frontend/
│   ├── components/           # React components
│   ├── services/
│   │   └── geminiService.ts  # STT/TTS services
│   └── types.ts
├── tts/                      # Standalone Streamlit TTS app
├── docs/
│   └── image.png             # README image
└── README.md

---

License

MIT