Kokoro-82M-int8-ov

• Model creator: hexgrad
• Original model: Kokoro-82M

[!WARNING] Disclaimer: This model is provided for evaluation purposes only. Performance, accuracy, and stability may vary. Use at your own discretion.

Description

This is Kokoro-82M model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF.

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.

Quantization Parameters

Weight compression was performed using nncf.compress_weights with the following parameters:

• mode: INT8_ASYM

For more information on quantization, check the OpenVINO model optimization guide.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• OpenVINO version 2026.3.0 and higher
• Optimum Intel 1.27.0 and higher

Running Model Inference with Optimum Intel

1. Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install -U "git+https://github.com/huggingface/optimum-intel.git" "kokoro" "misaki[en]" "soundfile"

As OpenVINO 2026.3.0 is not released yet, install the pre-release (nightly) build of OpenVINO to run this model:

pip install --pre -U openvino --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly

2. Run model inference:

import soundfile as sf
from optimum.intel.openvino import OVModelForTextToSpeechSeq2Seq

model_id = "OpenVINO/Kokoro-82M-int8-ov"
model = OVModelForTextToSpeechSeq2Seq.from_pretrained(model_id)

inputs = model.preprocess_input("Kokoro is an open-weight TTS model with 82 million parameters.", voice="af_heart", lang_code="a")
audio = model.generate(**inputs)

sf.write("output.wav", audio.numpy(), 24000)

For more examples and possible optimizations, refer to the Inference with Optimum Intel.

You can find more detailed usage examples in OpenVINO Notebooks:

• Text-to-speech synthesis using Kokoro and OpenVINO

Running Model with OpenAI client and OpenVINO Model Server

1a. Deploy model on Windows using binary package:

mkdir C:\models
ovms.exe --rest_port 8000 --source_model OpenVINO/Kokoro-82M-int8-ov --model_repository_path C:\models

1b. Deploy model in a Docker container:

mkdir -p ${HOME}/models
docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v ${HOME}/models:/models:rw openvino/model_server:weekly \
--rest_port 8000 --model_repository_path /models --source_model OpenVINO/Kokoro-82M-int8-ov

2. Install the client library:

pip install openai

3. Run the client:

from openai import OpenAI
client = OpenAI(
  base_url="http://localhost:8000/v1",
  api_key="unused"
)

with client.audio.speech.with_streaming_response.create(
  model="OpenVINO/Kokoro-82M-int8-ov",
  voice="af_alloy",
  input="The quick brown fox jumped over the lazy dog"
) as response:
  response.stream_to_file("speech.wav")


print("Generation finished")

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under the apache-2.0 license. More details can be found in the original model card.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.