Tts Ru Free Hf Vits High Multispeaker
T
Tts Ru Free Hf Vits High Multispeaker
Developed by utrobinmv
This is a Russian text-to-speech model supporting multiple speakers, capable of directly processing plain text with punctuation without the need for prior conversion to phonemes.
Downloads 182
Release Time : 5/25/2024
Model Overview
This model is a Russian text-to-speech (TTS) model with multi-speaker functionality, including both female and male voices. It features automatic stress marking capability, and it is recommended to manually add stress marks before vowel letters to improve generation quality.
Model Features
Multi-speaker support
The model includes two voices: No.0 - female voice, No.1 - male voice
Automatic stress marking
The model has automatic stress marking capability, but manual addition of stress marks is recommended for improved quality
Direct text processing
Can directly process plain text with punctuation without prior conversion to phonemes
Model Capabilities
Russian text-to-speech
Multi-speaker speech synthesis
Automatic stress marking
Use Cases
Speech synthesis applications
Audiobook generation
Convert Russian text into natural speech for audiobook production
Can generate speech content with distinct speaker characteristics
Voice assistant development
Provide high-quality speech synthesis capabilities for Russian voice assistants
Supports voice output options of different genders
Featured Recommended AI Models