Kokoro-82M-fp16-ov

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

Description

This is Kokoro-82M model converted to the OpenVINO™ IR (Intermediate Representation) format.

Compatibility

The provided OpenVINO™ IR model is compatible with:

• Optimum Intel built from the main branch

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" --extra-index-url https://download.pytorch.org/whl/cpu
pip install -U "openvino>=2026.4.0"

2. Run model inference:

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

model_id = "OpenVINO/Kokoro-82M-fp16-ov"
model = OVModelForTextToSpeechSeq2Seq.from_pretrained(model_id)

inputs = model.preprocess_input("Hello, this is a text to speech example.")
audio = model.generate(**inputs)

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

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

You can find more detailed usage examples in OpenVINO Notebooks:

• Kokoro-82M

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under Apache License Version 2.0 license. More details can be found in Kokoro-82M.

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.