Simple script to try out https://github.com/hexgrad/kokoro

speak.py

# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "click",
#     "kokoro",
#     "misaki[en]",
#     "soundfile",
# ]
# ///
import click
from kokoro import KPipeline
import soundfile as sf


def speak(text):
    pipeline = KPipeline(lang_code="a")
    generator = pipeline(text, voice="af_heart", speed=1, split_pattern=r"\n+")
    for i, (gs, ps, audio) in enumerate(generator):
        sf.write(f"{i}.wav", audio, 24000)  # save each audio file
        print(f"{i}.wav")


@click.command()
@click.argument("text")
def main(text: str) -> None:
    """Speak the given text."""
    speak(text)


if __name__ == "__main__":
    main()