tts-api / test.py
Avinyaa
u
1b567fa
raw
history blame
984 Bytes
import os
# Set basic environment variables
os.environ['NUMBA_DISABLE_JIT'] = '1'
from kokoro import KPipeline
import soundfile as sf
import torch
# Initialize Kokoro pipeline
pipeline = KPipeline(lang_code='a')
# Text to convert to speech
text = '''
[Kokoro](/kˈOkəɹO/) is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, [Kokoro](/kˈOkəɹO/) can be deployed anywhere from production environments to personal projects.
'''
# Generate speech using Kokoro
generator = pipeline(text, voice='af_heart')
# Process and save the generated audio
for i, (gs, ps, audio) in enumerate(generator):
print(f"Segment {i}: gs={gs}, ps={ps}")
# Save each segment as a separate file
sf.write(f'{i}.wav', audio, 24000)
print(f"Saved segment {i} as {i}.wav")
print("Speech generation completed!")