AIbase
EN
Home
Kokoro V1 0
K

Kokoro V1 0

Developed by kiriyamaX
Kokoro is an open-source text-to-speech model with 82 million parameters, achieving sound quality comparable to large models with a lightweight architecture while improving generation speed and reducing computational costs.
Speech Synthesis EnglishOpen Source License:Apache-2.0#Lightweight TTS#High-fidelity speech synthesis#Fast inference
Downloads 18
Release Time : 2/4/2025

Model Overview

A customized voice model licensed under Apache, suitable for text-to-speech tasks in production environments or personal projects.

Model Features

Lightweight and efficient
Only 82 million parameters achieve voice quality comparable to large models
Fast generation
Optimized architecture significantly improves inference speed
Open-source commercial use
Apache-2.0 license allows free deployment in commercial projects

Model Capabilities

High-fidelity speech synthesis
English text-to-speech
Real-time voice generation

Use Cases

Content creation
Audiobook generation
Convert e-book text into natural speech
Sample audio demonstrates smooth reading effects
Assistive technology
Voice assistant
Provide voice interaction capabilities for applications
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase