Kokoro is an open-source TTS model with 82 million parameters, delivering audio quality comparable to larger models while offering significant speed advantages and cost efficiency.
Kokoro is a lightweight text-to-speech model based on the StyleTTS2 architecture, supporting multiple languages and voice styles, suitable for both production environments and personal projects.
Model Features
Lightweight and Efficient
82 million parameter lightweight architecture that maintains high-quality audio while enabling fast inference.
Multilingual Support
Supports 8 languages and 54 voice styles to meet diverse needs.
Open-Source License
Licensed under Apache-2.0, freely available for commercial and personal projects.
Low-Cost Training
Training completed for just $1,000 using A100 GPUs.
Model Capabilities
High-quality speech synthesis
Multilingual voice generation
Voice style switching
Speech rate adjustment
Use Cases
Content Creation
Audiobook Generation
Convert text content into natural speech.
Produces high-quality, expressive voice output.
Video Dubbing
Add multilingual voiceovers to video content.
Supports voice output in multiple languages and styles.
Assistive Technology
Voice Assistant Applications
Provide text-to-speech functionality for visually impaired users.
Generates clear and natural voice output.
🚀 Kokoro - An Open-Weight TTS Model
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it offers comparable quality to larger models while being significantly faster and more cost - efficient. With Apache - licensed weights, it can be deployed in various scenarios, from production environments to personal projects.
⬆️ Kokoro has been upgraded to v1.0! See Releases.
You can quickly start using Kokoro by following the steps in the Usage section. You can also install it via pip install kokoro as described in the documentation.
✨ Features
Lightweight and High - Quality: With only 82 million parameters, it can achieve comparable quality to larger models.
Fast and Cost - Efficient: Offers faster performance and lower costs.
Flexible Deployment: Thanks to its Apache - licensed weights, it can be deployed in various environments.
# 1️⃣ Install kokoro
!pip install -q kokoro>=0.3.4 soundfile
# 2️⃣ Install espeak, used for English OOD fallback and some non-English languages
!apt-get -qq -y install espeak-ng > /dev/null 2>&1# 🇪🇸 'e' => Spanish es# 🇫🇷 'f' => French fr-fr# 🇮🇳 'h' => Hindi hi# 🇮🇹 'i' => Italian it# 🇧🇷 'p' => Brazilian Portuguese pt-br# 3️⃣ Initalize a pipelinefrom kokoro import KPipeline
from IPython.display import display, Audio
import soundfile as sf
# 🇺🇸 'a' => American English, 🇬🇧 'b' => British English# 🇯🇵 'j' => Japanese: pip install misaki[ja]# 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]
pipeline = KPipeline(lang_code='a') # <= make sure lang_code matches voice# This text is for demonstration purposes only, unseen during training
text = '''
The sky above the port was the color of television, tuned to a dead channel.
"It's not like I'm using," Case heard someone say, as he shouldered his way through the crowd around the door of the Chat. "It's like my body's developed this massive drug deficiency."
It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional expatriates; you could drink there for a week and never hear two words in Japanese.
These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures. The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need. We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so - called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.
[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.
'''# text = '「もしおれがただ偶然、そしてこうしようというつもりでなくここに立っているのなら、ちょっとばかり絶望するところだな」と、そんなことが彼の頭に思い浮かんだ。'# text = '中國人民不信邪也不怕邪,不惹事也不怕事,任何外國不要指望我們會拿自己的核心利益做交易,不要指望我們會吞下損害我國主權、安全、發展利益的苦果!'# text = 'Los partidos políticos tradicionales compiten con los populismos y los movimientos asamblearios.'# text = 'Le dromadaire resplendissant déambulait tranquillement dans les méandres en mastiquant de petites feuilles vernissées.'# text = 'ट्रांसपोर्टरों की हड़ताल लगातार पांचवें दिन जारी, दिसंबर से इलेक्ट्रॉनिक टोल कलेक्शनल सिस्टम'# text = "Allora cominciava l'insonnia, o un dormiveglia peggiore dell'insonnia, che talvolta assumeva i caratteri dell'incubo."# text = 'Elabora relatórios de acompanhamento cronológico para as diferentes unidades do Departamento que propõem contratos.'# 4️⃣ Generate, display, and save audio files in a loop.
generator = pipeline(
text, voice='af_heart', # <= change voice here
speed=1, split_pattern=r'\n+'
)
for i, (gs, ps, audio) inenumerate(generator):
print(i) # i => indexprint(gs) # gs => graphemes/textprint(ps) # ps => phonemes
display(Audio(data=audio, rate=24000, autoplay=i==0))
sf.write(f'{i}.wav', audio, 24000) # save each audio file
Under the hood, kokoro uses misaki, a G2P library at https://github.com/hexgrad/misaki
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[1] generated by closed[2] TTS models from large providers
[1] https://copyright.gov/ai/ai_policy_guidance.pdf
[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.