ggml-org/chatterbox-GGUF

chatterbox

Run it from the terminal:

llama-tts -hf ggml-org/chatterbox-GGUF -p "Hello world" --tts-lang en --output out.wav

Or with the server, using the /tts endpoint:

llama serve -hf ggml-org/chatterbox-GGUF

Source models

• https://huggingface.co/ResembleAI/chatterbox

Notes

• This is Chatterbox Multilingual V3 (23 languages), --tts-lang selects the language.
• --tts-speaker-file clones a reference voice (wav, mp3), the voice shipped with the model is used without it.
• Requires a llama.cpp build that includes https://github.com/ggml-org/llama.cpp/pull/31698
• See https://github.com/ggml-org/llama.cpp/blob/master/tools/tts/README.md#chatterbox

This model is automatically converted using https://github.com/ggml-org/convert