Kokoro

Kokoro is an open-weight text-to-speech model and inference library built around the lightweight Kokoro-82M model. It is designed to generate high-quality speech from text while staying fast, compact, and cost-efficient compared with larger TTS systems. The project is useful for developers who want deployable speech synthesis without depending on a closed platform. It can be installed as a Python package and used in applications, scripts, experiments, or production workflows. Kokoro’s Apache-licensed weights make it flexible for personal, research, and commercial use cases. Its main value is delivering practical, accessible voice generation with a small model footprint and a simple developer workflow.

Features

Open-weight TTS model
82 million parameter architecture
Python inference library
Apache-licensed model weights
Fast and cost-efficient speech generation
Suitable for local or production deployment

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow Kokoro

Kokoro Web Site

Other Useful Business Software

Host LLMs in Production With On-Demand GPUs

NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.

Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.

Try Free

Rate This Project

User Reviews

Be the first to post a review of Kokoro!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

JavaScript

Related Categories

JavaScript Text-to-Speech (TTS) Models

Registered

2026-06-08

Similar Business Software

Piper TTS

Piper is a fast, local neural text-to-speech (TTS) system optimized for devices like the Raspberry Pi 4, designed to deliver high-quality speech synthesis without relying on cloud services. It utilizes neural network models trained with VITS and exported to ONNX Runtime, enabling efficient and...

See Software
Chatterbox

Chatterbox is a free, open source voice cloning AI model developed by Resemble AI, licensed under MIT. It enables zero-shot voice cloning using just 5 seconds of reference audio, eliminating the need for training. The model offers expressive speech synthesis with unique emotion control, allowing...

See Software
Voxtral TTS

Voxtral TTS is a state-of-the-art, multilingual text-to-speech model designed to generate highly realistic and emotionally expressive speech from text, combining strong contextual understanding with advanced speaker modeling to produce natural, human-like audio output. Built as a lightweight...

See Software
Cartesia Sonic-3

Cartesia Sonic-3 is a real-time, streaming text-to-speech (TTS) model designed to generate ultra-realistic, expressive voice output with extremely low latency, enabling AI systems to speak as fluidly as humans in live interactions. Built on advanced state space model architecture, Sonic delivers...

See Software
EVI 3

Hume AI's EVI 3 is a third-generation speech-language model that streams in user speech and forms natural, expressive speech and language responses. At conversational latency, it produces the same quality of speech as our text-to-speech model, Octave. Simultaneously, it responds with the same...

See Software
Qwen3-TTS

Qwen3-TTS is an open source series of advanced text-to-speech models developed by the Qwen team at Alibaba Cloud under the Apache-2.0 license, offering stable, expressive, and real-time speech generation with features such as voice cloning, voice design, and fine-grained control of prosody and...

See Software