VITS TTS-värden
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Radera din text i SSML-taggar för exakt kontroll:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Taggar den valda modellen förstår — klicka för att släppa en i din text där det händer:
Den här modellen läser vanlig text, så inline-taggar ignoreras. För taggbaserade känslor, byt till en uttrycksfull modell som Orpheus eller Bark.
Definiera egna uttal (ord = uttal):
Om jag inte kan 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.
Bäst för: General-purpose text-to-speech with natural prosody
Bläddra alla VITS rösterMed en blick
- Utvecklare
- Jaehyeon Kim et al.
- Licens
- MIT
- Nivå
- free
- Varvtal
- fast
- Röstkloning
- Ej tillämpligt
- Språk
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Max tecken
- 2000