Kokoro-82M

Repository
hexgrad/Kokoro-82M
Engine
vLLM
Listed
9 Nov 2026

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

Serves
Speech
Weights
363 MB
License
Apache-2.0

Capabilities

Read from the model's capability tags. Requests are admitted per tag.

Speech speech
  • POST /v1/audio/speech

Endpoint task mode speech

Inputs
Text

Launch settings

Every engine serving the model starts with these. An image or audio pipeline holds no token KV cache and does not decode token by token, so quantization, KV cache dtype and speculative decoding do not apply.

Set by the owner. auto: the serving node derives it. default: the platform's value, left in place.

Engine
vLLM
Scheduling policy --scheduling-policy
priority default
Interactive requests ahead of batch work; same-class traffic in arrival order.
Trust remote code --trust-remote-code
on default
Python shipped in the bundle may run at load (the default).

Engine tuning

Every setting auto: the serving node derives each one.

Set by the owner. auto: the serving node derives it.

Memory and batching

GPU memory utilization --gpu-memory-utilization
auto
Max sequences --max-num-seqs
auto
Max batched tokens --max-num-batched-tokens
auto

Execution

Enforce eager --enforce-eager
auto
Async scheduling --no-async-scheduling
auto
Custom all-reduce --disable-custom-all-reduce
auto

Architecture

Read from the model's files at upload.

Architecture
KokoroForConditionalGeneration
Layers num_hidden_layers
3
Weights on disk
363 MB, unknown

Call it

Create an endpoint for the model, then send it a request in the OpenAI shape.

Shell
# Create an endpoint for this model, then provision it. # --tier-id is the service tier to run on; pick one at /endpoints/new. erectl endpoints create \ --name "My endpoint" \ --slug my-endpoint \ --model-id 537D07C3-61F7-40A5-86EC-5461C67E96C2 \ --task-mode speech \ --tier-id <tier-id> # provision takes the endpoint UUID returned by create erectl endpoints provision <endpoint-id> # Call it. Requests are routed by /<project-id>/<endpoint-slug>. curl https://api.erebine.ai/proj_ABC123/my-endpoint/v1/audio/speech \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $EREBINE_API_KEY" \ -d '{"model": "Kokoro-82M", "input": "The layer underneath.", "voice": "af_alloy"}' \ --output speech.mp3

Model card

As published with hexgrad/Kokoro-82M. Images are left out; its HTML tables are set as tables.

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.

🚀 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

ModelPublishedTraining DataLangs & VoicesSHA256
v1.02025 Jan 27Few hundred hrs8 & 54496dba11
v0.192024 Dec 25<100 hrs1 & 103b0c392f
Training Costsv0.19v1.0Total
in A100 80GB GPU hours5005001000
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.
!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](/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.
'''
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[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.

Audio DataDuration UsedLicenseAdded to Training Set After
Koniwa tnc<1hCC BY 3.0v0.19 / 22 Nov 2024
SIWIS<11hCC BY 4.0v0.19 / 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
  • 🪽 Kokoro is a Japanese word that translates to "heart" or "spirit". It is also the name of an AI in the Terminator franchise.