Skip to content
AI Tutorials
Text-to-Speech
Chatterbox

Install Chatterbox TTS with Conda

Introduction

Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages.

GitHub: https://github.com/resemble-ai/chatterbox
Hugging Face: https://hf.co/ResembleAI
Demo: https://hf.co/spaces/ResembleAI/Chatterbox-Multilingual-TTS
Docs: https://docs.resemble.ai/voice-generation/text-to-speech
Audio Samples: https://resemble-ai.github.io/chatterbox_demopage/

Prerequisites

System requirements:

  • Operating System: Windows 10/11 (64-bit), macOS, or Linux (Debian/Ubuntu).
  • Python: version >= 3.10 required
  • Disk Space: 10GB+ recommended (for dependencies and model cache). At least 400 MB for Miniconda; 3 GB+ for full Anaconda.
  • The GPU is optional but HIGHLY Recommended for Performance
  • Internet: For downloading dependencies and models from Hugging Face Hub.
Requirements CPU RAM
Minimum Intel Core i3 or AMD Ryzen 3 8 GB
Recommended Intel Core i5 or AMD Ryzen 5 16 GB
High-performance Intel Core i7/i9 or AMD Ryzen 7/9 32 GB
Environment Run this Command
CPU only pip3 install torch torchvision
Apple Silicon pip3 install torch torchvision
AMD ROCm Install PyTorch for ROCm
CUDA 11.8 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
CUDA 12.1 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
CUDA 12.6 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
CUDA 12.8 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
CUDA 13.0 pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu130

Video tutorial

Step 1. Install Miniconda Package

Step 2. Create Conda Environment

Create a conda environment:

name: chatterbox
channels:
- conda-forge
- defaults
dependencies:
# Python version >= 3.11 required
- python=3.11

- pip
- pip:
    # PyTorch CPU only
    - torch
    - torchaudio

    # Chatterbox TTS
    - chatterbox-tts
    - "resemble-perth @ git+https://github.com/resemble-ai/Perth.git@master"

Activate conda environment:

conda env create -f environment.yml
conda activate chatterbox

Step 3. Create a Python Script

Create a file named chatterbox_test.py:

import torchaudio as ta
import torch
from chatterbox.tts_turbo import ChatterboxTurboTTS

# Automatically detect the best available device
if torch.cuda.is_available():
    device = "cuda"
elif torch.backends.mps.is_available():
    device = "mps"
else:
    device = "cpu"

print(f"Using device: {device}")

# Load the Turbo model
model = ChatterboxTurboTTS.from_pretrained(device)

# Generate with Paralinguistic Tags
text = "Hi there, Sarah here from MochaFone calling you back [chuckle], have you got one minute to chat about the billing issue?"

# Generate audio
wav = model.generate(text)

ta.save("test.wav", wav, model.sr)

Run it:

python chatterbox_test.py

The result will be the audio file test.wav

Launch the local web UI

Try Chatterbox without coding:

python gradio_tts_app.py

Open your browser and navigate to http://127.0.0.1:7860. The system will automatically download the required model weights from HuggingFace during this first run.

Note: You can download the gradio_tts_app.py file here.

BreezeCuteTTS