AIbase
EN
Home
Kotoba Speech V0.1
K

Kotoba Speech V0.1

Developed by kotoba-tech
Kotoba-Speech v0.1 is a Japanese speech generation model based on a 1.2B parameter Transformer, supporting text-to-speech and one-shot voice cloning.
Speech Synthesis
Transformers
 JapaneseOpen Source License:Apache-2.0#Japanese TTS#Voice Cloning#1.2B Parameters
Downloads 23
Release Time : 3/14/2024

Model Overview

This model is an end-to-end Transformer architecture speech generation model, focusing on Japanese text-to-speech and voice cloning capabilities.

Model Features

Fluent Japanese Speech Generation
Capable of converting Japanese text into natural and fluent speech.
One-Shot Voice Cloning
Achieves voice cloning with just one sample through voice prompts.
Large Parameter Scale
Based on a 1.2B parameter Transformer architecture, delivering high-quality speech generation.

Model Capabilities

Japanese Text-to-Speech
Voice Cloning
Speech Synthesis

Use Cases

Voice Interaction
Voice Assistant
Provides natural and fluent speech output for Japanese voice assistants.
Enhances user experience with naturalness.
Content Creation
Audiobook Generation
Automatically converts Japanese text into audiobooks.
Efficiently generates high-quality speech content.
Personalized Services
Personalized Voice Cloning
Clones specific individuals' voices with minimal samples.
Enables personalized voice services.
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