Run it from the terminal:
llama-tts -hf ggml-org/Soprano-1.1-80M-GGUF -p "Hello world" --output out.wav
Or with the server, using the /tts endpoint:
llama serve -hf ggml-org/Soprano-1.1-80M-GGUF
[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert
ekwek/Soprano-1.1-80M