Add Chatterbox TTS as a TTS Backend

[localai-bot]

Feature Request: Add Chatterbox TTS as a TTS Backend

Overview

Chatterbox TTS is an open-source text-to-speech model with zero-shot generation, emotion control, and low latency. Integrating it as a backend would enhance LocalAI's capabilities for voice-driven applications.

Integration Steps

1. Add Configuration Option: Introduce a tts_backend parameter in the configuration file to switch between TTS providers (e.g., chatterbox, elevenlabs, etc.).
2. Implement Chatterbox Support: Use the chatterbox-tts Python package to handle text-to-speech generation.
3. Update Documentation: Add instructions for enabling and using Chatterbox TTS in the README or documentation.
4. Testing: Ensure the integration works with sample prompts and edge cases.

Acceptance Criteria

• Chatterbox TTS is successfully integrated as a backend option.
• Documentation is updated with usage examples.
• Tests confirm the backend functions correctly.
• No breaking changes to existing TTS implementations.

Why This Matters

Chatterbox TTS offers a lightweight, high-quality alternative to closed-source solutions, making it ideal for developers seeking flexibility and performance.