---
Chatterbox TTS Pro is a high-quality, customizable text-to-speech (TTS) system enhanced with voice presets, advanced audio effects, and conversation mode, With 23 Languages. This is a fork of Resemble AI's Chatterbox, extended with additional audio controls, export options, and a powerful UI via Gradio.
-
🎤 Voice Presets
Save and load voice settings including reference audio for fast reuse. -
🎛️ Advanced Audio Effects
Add reverb, echo, pitch shifting, equalizer, 3D spatialization, and noise reduction. -
🧠 Conversation Mode
Generate multi-speaker dialogues with different voice presets. -
📦 Export Options
Export audio in high/medium/low quality WAV formats. -
🎚️ Dynamic Controls
Modify chunk size, temperature, seed, and more to fine-tune output.
git clone https://github.com/SUP3RMASS1VE/chatterbox-SUP3R.git
cd chatterbox-SUP3R
python -m venv venv
venv\Scripts\activate
pip install --upgrade pip
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
pip install -r requirements.txt
pip install chatterbox-tts --no-deps --force-reinstallRun the app with:
python app.pyThis will launch a Gradio-based interface in your browser where you can:
- Enter text and generate speech
- Upload reference audio
- Enable advanced audio effects
- Save/load/delete voice presets
- Generate conversations between multiple speakers
app.py— Main application logicvoice_presets.json— Stores saved voice preset metadatasaved_voices/— Stores reference audio filesexports/— Output directory for exported audio
Use this format to define dialogues:
Alice: Hey Bob, how's it going?
Bob: Doing great! Just testing Chatterbox.
Alice: Awesome, it sounds incredible.
Big thanks to the original creators of Chatterbox: 👉 Resemble AI for their groundbreaking work in controllable TTS.
This project is provided under the original license of the upstream chatterbox. Check their repository for licensing details.
Let me know if you’d like a more developer-focused or user-focused version!