Kokoro-82M
Run it from the terminal:
llama-tts -hf ggml-org/Kokoro-82M-GGUF -p "Hello world" --tts-voice af_heart --output out.wav
Or with the server, using the /tts endpoint:
llama serve -hf ggml-org/Kokoro-82M-GGUF
Source models
Notes
--tts-voiceselects one of the voices shipped with the model; its first letter is the language (aAmerican English,bBritish English,eSpanish,fFrench,hHindi,iItalian,pBrazilian Portuguese,jJapanese,zMandarin).- Text input is English only. For the other languages, the prompt must already be phonemes (e.g. from espeak-ng).
- See https://github.com/ggml-org/llama.cpp/blob/master/docs/multimodal/tts.md#kokoro
[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert