ScriptsMar 31, 2026·2 min read

Kokoro — Lightweight 82M TTS in 9 Languages

Kokoro is an 82M parameter text-to-speech model delivering quality comparable to larger models. 6.2K+ GitHub stars. Supports English, Spanish, French, Japanese, Chinese, and more. Apache 2.0.

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

# Install
pip install kokoro

# Generate speech
python -c "
from kokoro import KPipeline
pipe = KPipeline(lang_code='a')  # 'a' = American English
generator = pipe('Hello, this is Kokoro text to speech!', voice='af_heart')
for i, (gs, ps, audio) in enumerate(generator):
    pass  # audio is a numpy array
import soundfile as sf
sf.write('hello.wav', audio, 24000)
print('Saved hello.wav')
"
Intro

Kokoro is an open-weight text-to-speech model with just 82 million parameters that delivers quality comparable to much larger models while being faster and more cost-efficient. With 6,200+ GitHub stars and Apache 2.0 license, Kokoro supports 9 languages: American English, British English, Spanish, French, Italian, Hindi, Japanese, Brazilian Portuguese, and Mandarin Chinese. It features streaming audio generation, runs on CPU and Apple Silicon GPU, and uses the misaki library for grapheme-to-phoneme conversion.

Best for: Developers needing lightweight, high-quality TTS without large GPU requirements Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf Languages: English (US/UK), Spanish, French, Italian, Hindi, Japanese, Portuguese, Chinese

Key Features

  • 82M parameters: Lightweight yet high-quality speech synthesis
  • 9 languages: English, Spanish, French, Italian, Hindi, Japanese, Portuguese, Chinese
  • Apache 2.0 weights: Unrestricted commercial deployment
  • Streaming audio: Generator-based interface for real-time output
  • CPU + Apple Silicon: Runs efficiently without NVIDIA GPU
  • Multiple voices: Various speaker styles per language
  • Cost-efficient: Fraction of the compute cost of larger TTS models

FAQ

Q: What is Kokoro? A: Kokoro is an 82M parameter TTS model with 6.2K+ stars delivering quality comparable to larger models in 9 languages. Apache 2.0 licensed, runs on CPU and Apple Silicon.

Q: How do I install Kokoro? A: Run pip install kokoro. Use KPipeline(lang_code='a') for American English, then generate speech with the pipe() method.

🙏

Source & Thanks

Created by Hexgrad. Licensed under Apache 2.0. hexgrad/kokoro — 6,200+ GitHub stars

Related Assets

GPT4All — Run LLMs Privately on Your Desktop

GPT4All runs large language models privately on everyday desktops and laptops without GPUs or API calls. 77.2K+ GitHub stars. Desktop app + Python SDK, LocalDocs for private data. MIT licensed.

TokRepo精选

vLLM — High-Throughput LLM Serving Engine

vLLM is a high-throughput and memory-efficient LLM inference engine. 74.8K+ GitHub stars. PagedAttention, continuous batching, OpenAI-compatible API, multi-GPU serving. Apache 2.0.

TokRepo精选

llama.cpp — Run LLMs Locally in Pure C/C++

llama.cpp is a C/C++ LLM inference engine with 100K+ GitHub stars. Runs on CPU, Apple Silicon, NVIDIA, AMD GPUs. 1.5-8 bit quantization, no dependencies, supports 50+ model architectures. MIT licensed

TokRepo精选
◈Home🏆Trending👤Me