Kokoro 82M

提供商hexgrad
分类text-to-speech
许可证apache-2.0
下载量6.7K
星标1

简介

Kokoro 82M 是一款极具性价比的轻量级文本转语音 (TTS) 模型。它最核心的竞争力在于用极小的参数量（仅 82M）实现了媲美大型模型的自然语音合成效果，有效解决了端侧部署时显存占用高和推理延迟大的痛点。对于开发者而言，它非常适合集成到个人助手、轻量级阅读软件或对响应速度要求极高的实时交互场景中。由于采用了 Apache-2.0 开源协议，且上手门槛极低，你可以将其视为一个高性能、可本地化部署的开源语音合成引擎，是替代昂贵 API 服务的理想方案。

核心亮点

  • 极小参数量实现高自然度语音合成
  • 端侧推理速度极快，低延迟响应
  • Apache-2.0 协议，支持商业化自由部署
  • 适合集成至轻量级 AI 助手或阅读工具

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("hexgrad/Kokoro-82M")
tokenizer = AutoTokenizer.from_pretrained("hexgrad/Kokoro-82M")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download hexgrad/Kokoro-82M

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download hexgrad/Kokoro-82M config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('hexgrad/Kokoro-82M')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/hexgrad/Kokoro-82M

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/hexgrad/Kokoro-82M

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('hexgrad/Kokoro-82M')
tokenizer = AutoTokenizer.from_pretrained('hexgrad/Kokoro-82M')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model hexgrad/Kokoro-82M

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model hexgrad/Kokoro-82M README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('hexgrad/Kokoro-82M')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/hexgrad/Kokoro-82M.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/hexgrad/Kokoro-82M.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'hexgrad/Kokoro-82M')

完整文档

来源: HuggingFace

---
license: apache-2.0
language:

  • en

base_model:
  • yl4579/StyleTTS2-LJSpeech

pipeline_tag: text-to-speech
---
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.

<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" type="audio/wav"></audio>

🐈 GitHub: https://github.com/hexgrad/kokoro

🚀 Demo: https://hf.co/spaces/hexgrad/Kokoro-TTS

> [!NOTE]
> As of April 2025, the market rate of Kokoro served over API is under $1 per million characters of text input, or under $0.06 per hour of audio output. (On average, 1000 characters of input is about 1 minute of output.) Sources: ArtificialAnalysis/Replicate at 65 cents per M chars and DeepInfra at 80 cents per M chars.
>
> This is an Apache-licensed model, and Kokoro has been deployed in numerous projects and commercial APIs. We welcome the deployment of the model in real use cases.

> [!CAUTION]
> Fake websites like kokorottsai_com (snapshot: https://archive.ph/nRRnk) and kokorotts_net (snapshot: https://archive.ph/60opa) are likely scams masquerading under the banner of a popular model.
>
> Any website containing "kokoro" in its root domain (e.g. kokorottsai_com, kokorotts_net) is NOT owned by and NOT affiliated with this model page or its author, and attempts to imply otherwise are red flags.

Releases

| Model | Published | Training Data | Langs & Voices | SHA256 |
| ----- | --------- | ------------- | -------------- | ------ |
| v1.0 | 2025 Jan 27 | Few hundred hrs | 8 & 54 | 496dba11 |
| v0.19 | 2024 Dec 25 | <100 hrs | 1 & 10 | 3b0c392f |

| Training Costs | v0.19 | v1.0 | Total |
| -------------- | ----- | ---- | ----- |
| in A100 80GB GPU hours | 500 | 500 | 1000 |
| average hourly rate | $0.80/h | $1.20/h | $1/h |
| in USD | $400 | $600 | $1000 |

Usage

You can run this basic cell on Google Colab. Listen to samples. For more languages and details, see Advanced Usage.
py
!pip install -q kokoro>=0.9.2 soundfile
!apt-get -qq -y install espeak-ng > /dev/null 2>&1
from kokoro import KPipeline
from IPython.display import display, Audio
import soundfile as sf
import torch
pipeline = KPipeline(lang_code='a')
text = '''
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.
'''
generator = pipeline(text, voice='af_heart')
for i, (gs, ps, audio) in enumerate(generator):
    print(i, gs, ps)
    display(Audio(data=audio, rate=24000, autoplay=i==0))
    sf.write(f'{i}.wav', audio, 24000)
Under the hood, kokoro uses misaki, a G2P library at https://github.com/hexgrad/misaki

Model Facts

Architecture:

  • StyleTTS 2: https://arxiv.org/abs/2306.07691

  • ISTFTNet: https://arxiv.org/abs/2203.02395

  • Decoder only: no diffusion, no encoder release

Architected by: Li et al @ https://github.com/yl4579/StyleTTS2

Trained by: @rzvzn on Discord

Languages: Multiple

Model SHA256 Hash: 496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4

Training Details

Data: Kokoro was trained exclusively on permissive/non-copyrighted audio data and IPA phoneme labels. Examples of permissive/non-copyrighted audio include:

  • Public domain audio

  • Audio licensed under Apache, MIT, etc

  • Synthetic audio<sup>[1]</sup> generated by closed<sup>[2]</sup> TTS models from large providers<br/>

[1] https://copyright.gov/ai/ai_policy_guidance.pdf<br/>
[2] No synthetic audio from open TTS models or "custom voice clones"

Total Dataset Size: A few hundred hours of audio

Total Training Cost: About $1000 for 1000 hours of A100 80GB vRAM

Creative Commons Attribution

The following CC BY audio was part of the dataset used to train Kokoro v1.0.

| Audio Data | Duration Used | License | Added to Training Set After |
| ---------- | ------------- | ------- | --------------------------- |
| Koniwa tnc | <1h | CC BY 3.0 | v0.19 / 22 Nov 2024 |
| SIWIS | <11h | CC BY 4.0 | v0.19 / 22 Nov 2024 |

Acknowledgements

  • 🛠️ @yl4579 for architecting StyleTTS 2.
  • 🏆 @Pendrokar for adding Kokoro as a contender in the TTS Spaces Arena.
  • 📊 Thank you to everyone who contributed synthetic training data.
  • ❤️ Special thanks to all compute sponsors.
  • 👾 Discord server: https://discord.gg/QuGxSWBfQy

<img src="https://static0.gamerantimages.com/wordpress/wp-content/uploads/2024/08/terminator-zero-41-1.jpg" width="400" alt="kokoro" />

查看官方来源