bhimrazy/chatterbox-tts repository overview

⁠🧠 Production-Ready Text-to-Speech API with Chatterbox TTS & LitServe

Chatterbox TTS is a state-of-the-art, open-source text-to-speech system developed by Resemble AI⁠. It supports zero-shot voice cloning, emotion control, and high-quality audio generation, all MIT-licensed and fully production-ready.

This Docker image wraps Chatterbox TTS in a scalable API using LitServe⁠, making it super easy to deploy, clone voices, and generate speech from text.

⁠📦 Quick Start with Docker

⁠Pull & Run the Container

docker run -p 8000:8000 bhimrazy/chatterbox-tts:v0.1.0

⁠Enable GPU Acceleration

docker run --gpus all -p 8000:8000 bhimrazy/chatterbox-tts:v0.1.0

⁠🎯 API Endpoints

• POST /speech – Generate speech from text, with optional voice cloning

⁠🧪 Example Usage

⁠🧵 Python: Basic Text-to-Speech

import requests

url = "http://127.0.0.1:8000/speech"
data = {
    "text": "Hello! This is a test of the Chatterbox TTS API.",
    "exaggeration": 0.5,
    "cfg": 0.5,
    "temperature": 0.8
}

response = requests.post(url, json=data)

with open("output.wav", "wb") as f:
    f.write(response.content)

⁠🧬 Voice Cloning with Local Audio File

data = {
    "text": "This will sound like the reference speaker!",
    "audio_prompt": "path/to/reference/audio.wav",
    "exaggeration": 0.7,
    "cfg": 0.3
}

response = requests.post(url, json=data)

⁠📦 Voice Cloning with Base64 Audio

import base64

with open("reference.wav", "rb") as f:
    audio_data = f.read()
audio_base64 = base64.b64encode(audio_data).decode('utf-8')

data = {
    "text": "Voice cloning with base64 encoded audio!",
    "audio_prompt": audio_base64,
    "exaggeration": 0.6,
    "cfg": 0.4
}

response = requests.post("http://127.0.0.1:8000/speech", json=data)

⁠🧾 Curl Example

curl -X POST http://127.0.0.1:8000/speech \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from curl!",
    "exaggeration": 0.5,
    "cfg": 0.5,
    "temperature": 0.8
  }' --output output.wav

⁠🔗 Resources

• 🧠 Chatterbox TTS GitHub: github.com/resemble-ai/chatterbox⁠
• 🚀 LitServe GitHub: github.com/Lightning-AI/litserve⁠
• 📘 Full API Codebase: github.com/bhimrazy/litserve-examples⁠
• 🌐 Lightning Studio: lightning.ai/bhimrajyadav⁠
• 🤗 Hugging Face Model: huggingface.co/ResembleAI/chatterbox⁠

⁠🔧 Parameters Overview

⁠🛠️ Use Cases

• 🎮 Game characters with emotional dialogue
• 🧑‍💼 AI assistants that sound real
• 🎙️ Podcast / audiobook narration
• 🎬 Automated video voice-overs
• 🌍 Multilingual content with consistent branding

⁠👋 Get Involved

If you're working on voice AI, creative tools, or AI-powered agents — let’s connect! You can follow or fork the repo, and feel free to open issues or contribute enhancements.