T

Tts Ru Free Hf Vits Low Multispeaker

Developed by utrobinmv
A Russian text-to-speech model supporting multiple speakers, capable of directly processing plain text with punctuation without prior conversion to phonemes.
Downloads 1,021
Release Time : 4/28/2024

Model Overview

This model offers two speaker voices (female and male), supports direct processing of plain Russian text, and recommends using stress annotation for optimal results.

Model Features

Multi-speaker support
Provides two speaker voice options: 0 - female voice, 1 - male voice
Direct text processing
Can directly process plain text with punctuation without prior conversion to phonemes
Lightweight model
The model has only 15.1 million parameters, with low resource consumption
Stress annotation support
Supports stress annotation to improve generation quality, recommends using the ruaccent library for annotation

Model Capabilities

Russian Text-to-Speech
Multi-speaker speech generation
Direct plain text processing

Use Cases

Speech synthesis applications
Audiobook generation
Convert Russian text into natural speech for audiobook production
Can generate speech with distinct speaker characteristics
Voice assistant
Provide speech synthesis capabilities for Russian voice assistants
Supports switching between male and female voices to enhance user experience
Assistive technology
Visual impairment assistance
Convert Russian text into speech to help visually impaired individuals access information
Provides clear and natural speech output
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase