Convert text to speech with different voices
Generate speech from text with adjustable speed
Generate high-quality speech from text with specified emotion and voice
✨[With v1.0.0] Accelerated TTS on Kokoro-82M
Realtime implementation of Whisper large turbo
Generate speech from text with adjustable rate and pitch
MaskGCT TTS Demo
Turn Any Article to Podcast
Generate Vietnamese speech from text and reference audio
Text to Audio (Sound SFX) Generator
Convert audio to text and summarize highlights
MaskGCT TTS Demo
vits-uma-genshin-honkai is a state-of-the-art text-to-speech (TTS) model specifically designed to generate voices resembling popular characters from Genshin Impact and Honkai: Star Rail. This model leverages cutting-edge AI technology to synthesize high-quality, natural-sounding speech that captures the unique tones and personalities of these beloved characters.
• Character Voice Support: Create speech with voices that mimic characters from Genshin Impact and Honkai: Star Rail.
• Multi-Language Support: Generate text-to-speech in multiple languages, including English, Chinese, and Japanese.
• Customizable Pitch and Speed: Adjust the pitch and speaking speed to match your desired output.
• High-Quality Audio: Produces clear and realistic audio with minimal artifacts.
• User-Friendly Interface: Easy-to-use interface for seamless text-to-speech conversion.
• Cross-Platform Compatibility: Works on multiple platforms, including Windows, macOS, and Linux.
What characters are supported by vits-uma-genshin-honkai?
The tool supports a wide range of characters from Genshin Impact and Honkai: Star Rail, including popular characters like Paimon, Diluc, and Kiana.
Can I use vits-uma-genshin-honkai for commercial projects?
Yes, vits-uma-genshin-honkai is available under a permissive license that allows for both personal and commercial use.
How do I fix audio generation issues?
If you encounter issues, ensure you have the latest version installed and check that all dependencies are correctly configured.