efemaer

# 1. https://docs.beam.cloud/v2/getting-started/quickstart#installation
# 2. beam deploy kokoro_beam.py:generate_speech

from beam import endpoint, env, Image, Output


if env.is_remote():
    from kokoro import KPipeline
    import subprocess

efemaer

Kokoro-82M-v1.0 Performance Benchmark

Introduction

Kokoro 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 can be deployed anywhere from production environments to personal projects.

Source: https://huggingface.co/hexgrad/Kokoro-82M