Install Kokoro TTS Model Locally

 This video locally installs Kokoro which is a frontier TTS model for its size of 82 million parameters. It can be run anywhere.

!git clone https://huggingface.co/hexgrad/Kokoro-82M

%cd Kokoro-82M

!apt-get -qq -y install espeak-ng > /dev/null 2>&1

!pip install -q phonemizer torch transformers scipy munch

from models import build_model

import torch

device = 'cuda' if torch.cuda.is_available() else 'cpu'

MODEL = build_model('kokoro-v0_19.pth', device)

VOICE_NAME = [

    'af',

    'af_bella', 'af_sarah', 'am_adam', 'am_michael',

    'bf_emma', 'bf_isabella', 'bm_george', 'bm_lewis',][0]

VOICEPACK = torch.load(f'voices/{VOICE_NAME}.pt', weights_only=True).to(device)

print(f'Loaded voice: {VOICE_NAME}')

from kokoro import generate

text = "How could I know? It's an unanswerable question. Like asking an unborn child if they'll lead a good life. They haven't even been born."

audio, out_ps = generate(MODEL, text, VOICEPACK, lang=VOICE_NAME[0])

from IPython.display import display, Audio

display(Audio(data=audio, rate=24000, autoplay=True))

print(out_ps)