Resemble AI Releases SoTA Open-Source TTS Model, Chatterbox

Chatterbox TTS

• License: MIT
• GitHubRepo
• DemoPage

Introduction

We're excited to introduce Chatterbox, Resemble AI's first production-grade open-source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open-source TTS model to support emotion exaggeration control, a powerful feature that makes voices stand out. Try it now on our Hugging Face Gradio app!

Key Details

• State-of-the-art zeroshot TTS
• 0.5B Llama backbone
• Unique exaggeration/intensity control
• Ultra-stable with alignment-informed inference
• Trained on 0.5M hours of cleaned data
• Watermarked outputs
• Easy voice conversion script
• Outperforms ElevenLabs

Tips

• General Use: Default settings (exaggeration=0.5, cfg_weight=0.5) work well. If the reference speaker has a fast speaking style, lowering cfg_weight to around 0.3 can improve pacing.
• Expressive or Dramatic Speech: Lower cfg_weight values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher.

Installation

pip install chatterbox-tts

Or, install from source:

conda create -yn chatterbox python=3.11
conda activate chatterbox
git clone https://github.com/resemble-ai/chatterbox.git
cd chatterbox
pip install -e .

Usage

import torchaudio as ta
from chatterbox.tts import ChatterboxTTS
model = ChatterboxTTS.from_pretrained(device="cuda")
text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill."
wav = model.generate(text)
ta.save("test-1.wav", wav, model.sr)

Supported Languages

Currently, only English.

Acknowledgements

Cosyvoice, Real-Time-Voice-Cloning, HiFT-GAN, Llama 3, S3Tokenizer, Built-in PerTh Watermarking for Responsible AI

Extracting Watermark

import perth
import librosa
AUDIO_PATH = "YOUR_FILE.wav"
watermarked_audio, sr = librosa.load(AUDIO_PATH, sr=None)
watermarker = perth.PerthImplicitWatermarker()
watermark = watermarker.get_watermark(watermarked_audio, sample_rate=sr)
print(f"Extracted watermark: {watermark}")

Official Discord

Join us on Discord and let's build something awesome together!

Citation

If you find this model useful, please consider citing:

@misc{chatterboxtts2025,
  author       = {{Resemble AI}},
  title        = {{Chatterbox-TTS}},
  year         = {2025},
  howpublished = {\url{https://github.com/resemble-ai/chatterbox}},
  note         = {GitHub repository}
}

Disclaimer

Don't use this model to do bad things. Prompts are sourced from freely available data on the internet.

Checkout the repository for more details.