VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Bryt teksten i SSML- tagger for nøyaktig kontroll:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Merker den valgte modellen forstår – klikk for å slippe en i teksten der den skjer:
Denne modellen leser ren tekst, så merker i teksten blir ignorert. Bytt til en ekspressiv modell som Orfeus eller Bark for å bruke tagger.
Definer selvvalgte uttaler (ord = uttale):
Om 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.
Best for: General-purpose text-to-speech with natural prosody
Bla gjennom alle VITS stemmerMed et blikk
- Utvikler
- Jaehyeon Kim et al.
- Lisens
- MIT
- Nivå
- free
- Hastighet
- fast
- Stemmekloning
- Nei
- Språk
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Største antall tegn
- 2000