agentskillexchange Chatterbox State-of-the-Art Open Source Text-to-Speech
An agent skill built on Chatterbox by Resemble AI, a state-of-the-art open-source text-to-speech model with zero-shot voice cloning and multilingual synthesis. Generates natural-sounding speech from text with support for 23 languages, voice cloning from reference audio, and emotion/style control.
Installation
Use the upstream install or setup path that matches your environment:
- pip install chatterbox-tts
- git clone https://github.com/resemble-ai/chatterbox.git
- pip install -e .
Requirements and caveats from upstream:
conda create -yn chatterbox python=3.11
- 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.
- python
Basic usage or getting-started notes:
shell
Alternatively, you can install from source:
conda activate chatterbox
Extracted from upstream docs: https://raw.githubusercontent.com/resemble-ai/chatterbox/HEAD/README.md