travisvn/chatterbox-tts-api

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

65
/ 100
Established

This project helps integrate advanced text-to-speech capabilities into your existing AI workflows. You provide text and a voice sample, and it generates natural-sounding speech, even in a cloned voice across 22 languages. Anyone who builds or uses local AI applications, like those for content creation or automated assistants, would benefit.

554 stars. Available on PyPI.

Use this if you need a self-hosted, customizable text-to-speech solution that can seamlessly replace OpenAI's TTS API in applications like Open WebUI or AnythingLLM.

Not ideal if you prefer a cloud-based service for text-to-speech or if your current setup does not support CUDA, as there are known issues with non-CUDA environments.

AI-assistants voice-generation content-creation language-tools local-AI-development
Maintenance 6 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 25 / 25

How are scores calculated?

Stars

554

Forks

127

Language

Python

License

AGPL-3.0

Last pushed

Dec 23, 2025

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/travisvn/chatterbox-tts-api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.