Chatterbox TTS

_Made with ♥️ by

We're excited to introduce Chatterbox Multilingual, Resemble AI's first production-grade open source TTS model supporting 23 languages out of the box. 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 across languages. It's also the first open source TTS model to support emotion exaggeration control with robust multilingual zero-shot voice cloning. Try the english only version now on our English Hugging Face Gradio app.. Or try the multilingual version on our Multilingual Hugging Face Gradio app..

If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link). It delivers reliable performance with ultra-low latency of sub 200ms—ideal for production use in agents, applications, or interactive media.

Key Details

• Multilingual, zero-shot TTS supporting 23 languages
• SoTA zeroshot English 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
• Smart artifact cleaning with pause protection
• Support for custom pause tags [pause:xx]

Supported Languages

Arabic (ar) • Danish (da) • German (de) • Greek (el) • English (en) • Spanish (es) • Finnish (fi) • French (fr) • Hebrew (he) • Hindi (hi) • Italian (it) • Japanese (ja) • Korean (ko) • Malay (ms) • Dutch (nl) • Norwegian (no) • Polish (pl) • Portuguese (pt) • Russian (ru) • Swedish (sv) • Swahili (sw) • Turkish (tr) • Chinese (zh)

Tips

• General Use (TTS and Voice Agents):

  • Ensure that the reference clip matches the specified language tag. Otherwise, language transfer outputs may inherit the accent of the reference clip’s language. To mitigate this, set cfg_weight to 0.
  • The default settings (exaggeration=0.5, cfg_weight=0.5) work well for most prompts across all languages.
  • If the reference speaker has a fast speaking style, lowering cfg_weight to around 0.3 can improve pacing.

• Expressive or Dramatic Speech:

  • Try lower cfg_weight values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher.
  • Higher exaggeration tends to speed up speech; reducing cfg_weight helps compensate with slower, more deliberate pacing.

Installation

Option 1: Docker (Recommended for Production)

The easiest way to run Chatterbox with HTTP API support:

# Clone the repository
git clone https://github.com/resemble-ai/chatterbox.git
cd chatterbox

# Build and run with Docker Compose
docker-compose up -d

# The API will be available at http://localhost:8000

For GPU support, edit docker-compose.yml and uncomment the GPU configuration section.

Option 2: pip install

pip install chatterbox-tts

Option 3: 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 .

We developed and tested Chatterbox on Python 3.11 on Debian 11 OS; the versions of the dependencies are pinned in pyproject.toml to ensure consistency. You can modify the code or dependencies in this installation mode.

Optional: Enhanced Russian Text Processing

For improved Russian TTS with stress marks, install the optional Russian support:

pip install -e ".[russian]"

Note: This installs russian-text-stresser which requires spacy 3.6.x. Due to dependency conflicts with gradio's typer version requirements, this is provided as an optional feature. Without this package, Russian TTS will still work, but stress marks won't be automatically added to the text.

HTTP API

Chatterbox includes a FastAPI-based HTTP API for easy integration into your applications.

Running the API Server

# Install API dependencies
pip install fastapi uvicorn python-multipart

# Run the server
python api_server.py
# Or with uvicorn directly:
uvicorn api_server:app --host 0.0.0.0 --port 8000

API Endpoints

Health Check

curl http://localhost:8000/health

List Supported Languages

curl http://localhost:8000/languages

Generate Speech (English)

# Basic TTS
curl -X POST http://localhost:8000/tts \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello world!"}' \
  --output speech.wav

# With custom pause tags
curl -X POST http://localhost:8000/tts \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello[pause:0.5s]world!", "exaggeration": 0.7}' \
  --output speech.wav

Generate Speech with Voice Cloning

curl -X POST http://localhost:8000/tts/with-voice \
  -F "text=Hello world!" \
  -F "voice_file=@reference_voice.wav" \
  --output speech.wav

Generate Multilingual Speech

curl -X POST http://localhost:8000/tts/multilingual \
  -H "Content-Type: application/json" \
  -d '{"text": "Bonjour le monde!", "language_id": "fr"}' \
  --output speech.wav

API Documentation

When the server is running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

Usage

import torchaudio as ta
from chatterbox.tts import ChatterboxTTS
from chatterbox.mtl_tts import ChatterboxMultilingualTTS

# English example
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-english.wav", wav, model.sr)

# Multilingual examples
multilingual_model = ChatterboxMultilingualTTS.from_pretrained(device=device)

french_text = "Bonjour, comment ça va? Ceci est le modèle de synthèse vocale multilingue Chatterbox, il prend en charge 23 langues."
wav_french = multilingual_model.generate(spanish_text, language_id="fr")
ta.save("test-french.wav", wav_french, model.sr)

chinese_text = "你好，今天天气真不错，希望你有一个愉快的周末。"
wav_chinese = multilingual_model.generate(chinese_text, language_id="zh")
ta.save("test-chinese.wav", wav_chinese, model.sr)

# If you want to synthesize with a different voice, specify the audio prompt
AUDIO_PROMPT_PATH = "YOUR_FILE.wav"
wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH)
ta.save("test-2.wav", wav, model.sr)

# Using artifact cleaning feature
wav = model.generate(
    text="Hello[pause:0.5s]world!",  # Support [pause:xx] tag for adding pauses
    use_auto_editor=True,            # Enable artifact cleaning
    ae_threshold=0.06,               # Volume threshold (0-1)
    ae_margin=0.2                    # Boundary protection time (seconds)
)
ta.save("test-3.wav", wav, model.sr)

See example_tts.py and example_vc.py for more examples.

Acknowledgements

• Cosyvoice
• Real-Time-Voice-Cloning
• HiFT-GAN
• Llama 3
• S3Tokenizer

Built-in PerTh Watermarking for Responsible AI

Every audio file generated by Chatterbox includes Resemble AI's Perth (Perceptual Threshold) Watermarker - imperceptible neural watermarks that survive MP3 compression, audio editing, and common manipulations while maintaining nearly 100% detection accuracy.

Watermark extraction

You can look for the watermark using the following script.

import perth
import librosa

AUDIO_PATH = "YOUR_FILE.wav"

# Load the watermarked audio
watermarked_audio, sr = librosa.load(AUDIO_PATH, sr=None)

# Initialize watermarker (same as used for embedding)
watermarker = perth.PerthImplicitWatermarker()

# Extract watermark
watermark = watermarker.get_watermark(watermarked_audio, sample_rate=sr)
print(f"Extracted watermark: {watermark}")
# Output: 0.0 (no watermark) or 1.0 (watermarked)

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.