VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Wrap yako tenzi mu SSML tags kuti zvive nyore kudzora:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags iyo yakasarudzwa model inonzwisiswa — tinya kuti utore imwe muchinyorwa chako apo inoitika:
Iyi modhi inoverenga chete mazita ezvinyorwa, saka zvinyorwa zvinonyorwa mumitsara hazvina kutariswa. Kuti uwane pfungwa dziri mumitsara, chinja kune imwe modhi inoratidza pfungwa seOrpheus kana Bark.
Define custom pronunciations (word = pronunciation):
Chii VITS
VITS — Variational Inference with adversarial learning for end-to-end Text-to-Speech — was introduced by Jaehyeon Kim and collaborators in 2021 and became a foundational architecture for modern neural speech. Rather than the older two-stage pipeline, it synthesizes audio in a single parallel end-to-end pass, pairing a variational autoencoder with normalizing flows and a GAN-style adversarial training process to lift naturalness. At about 25M parameters and trained on ~585 hours, it produces natural prosody at fast inference speeds and supports multiple speakers. It serves as a solid general-purpose, free baseline and underpins many later models such as Piper and MeloTTS.
Yakanaka kune: General-purpose text-to-speech with natural prosody
Tarisa zvese VITS mazwiMufananidzo
- Developer
- Jaehyeon Kim et al.
- License
- MIT
- Tier
- free
- Speed
- fast
- Kutaura
- Hapana
- Zvinhu
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Max characters
- 2000