pip install kokoro
, and still 82M parameters.GitHub: https://github.com/hexgrad/kokoro
PyPI: https://pypi.org/project/kokoro/
Space: hexgrad/Kokoro-TTS
Join the community of Machine Learners and AI enthusiasts.
Sign Uppip install kokoro
, and still 82M parameters.1.0 and 0.23 are different models. 1.0 continued training from 0.23
Great news! Any plans for kids voices?
Thank you for your hard work.
Actually Kokoro can do anything Microsoft Edge tts does what about adding pitch support too? I don't think it's something to be embedded in the model tho I guess we have to do it as a post processing right?
Its now a "Stream" tab capped at 5k characters, but you can also Duplicate that space and that limit is automatically lifted, or just download & run the model locally.