K

Kokoro

Developed by geneing
Kokoro is a cutting-edge text-to-speech (TTS) model with 82 million parameters, released under Apache 2.0 license. Ranked #1 in TTS Spaces Arena, achieving higher Elo scores with fewer parameters and data.
Downloads 37
Release Time : 1/1/2025

Model Overview

Kokoro is a high-performance text-to-speech model supporting American and British English, capable of generating high-quality voice output.

Model Features

Efficient Parameter Utilization
With 82M parameters and less than 100 hours of training data, it ranks #1 in TTS Spaces Arena, demonstrating exceptional parameter efficiency.
Multi-Voice Support
Offers 10 unique voice packs supporting different vocal styles and accents.
Open-Source License
Released under Apache 2.0 license, allowing free use and modification.

Model Capabilities

Text-to-Speech
Multi-Voice Pack Support
High-Quality Speech Generation

Use Cases

Speech Synthesis
Voice Assistants
Used to generate natural voice responses for voice assistants.
High-quality voice output with near-human pronunciation.
Audiobooks
Converts text content into speech for audiobook production.
Smooth voice output suitable for extended listening.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase