F

Fish Speech 1.4

Developed by audo
Leading text-to-speech (TTS) model trained on 700,000 hours of multilingual audio data
Downloads 24
Release Time : 9/12/2024

Model Overview

Fish Speech V1.4 is a multilingual text-to-speech model supporting 8 languages including Chinese and English, suitable for speech synthesis and voice interaction scenarios.

Model Features

Multilingual support
Supports text-to-speech in 8 languages, including mainstream languages like Chinese and English
Large-scale training data
Trained on 700,000 hours of multilingual audio data, including 300,000 hours each for Chinese and English
Open-source availability
Source code released under BSD-3-Clause license, facilitating research and development

Model Capabilities

Text-to-speech
Multilingual speech synthesis
Voice interaction support

Use Cases

Voice interaction
Smart voice assistant
Provides natural and fluent voice output for smart devices
Enhances user experience
Content creation
Audiobook generation
Automatically converts text content into speech
Efficiently generates multilingual audio content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase