VITS

VITS TTS

The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.

Teken op vir 5 000 karakterbeperking

Oorvloei jou teks in SSML etiket vir presiese beheer:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Merk die gekose model verstaan ooit die woord ooit om een in jou teks te laat val waar dit gebeur:

Hierdie model lees gewone teks, so inlyn etiket word geignoreer. Vir etiket-gebaseerde emosie, wissel na 'n uitdrukkingende model soos Orpheus of Bark.

Definieer pasmaak uitspraak (woord = uitspraak):

-12 +12
0.5x 2.0x
Vry met Pyper, VITS, MiloTTS
Jou gegenereer oudio sal hier verskyn. Kies 'n model, invoer teks, en kliek Genereer.
Klank Genereer suksesvol
0:00
Aflaai klaar gemaak Aflaai klaar gemaak Skakel verstrek in 24h
Vryvlak: persoonlike gebruik. Kommonsielisensie van R5/m
Liefde TTS.ai, vertel jou vriende!

Aangaande 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.

Beste vir: General-purpose text-to-speech with natural prosody

Blaai deur almal VITS stemme

Met'n blik

Ontwikkelingvloeistof is minDeveloper
Jaehyeon Kim et al.
Lisensie
MIT
Tier
free
Spoed
fast
Stem kloning
Nee
Tale
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Voeg- agteraan- by Taal
2000

VITS stemme

CSS10 (Dutch)

Dutch
Beskikbaar Neutral

CSS10 (Finnish)

Finnish
Beskikbaar Neutral

CSS10 (French)

French
Beskikbaar Neutral

CSS10 (German)

German
Beskikbaar Neutral

CSS10 (Hungarian)

Hungarian
Beskikbaar Neutral

CSS10 (Spanish)

Spanish
Beskikbaar Neutral

Common Voice (Bulgarian)

Bulgarian
Beskikbaar Neutral

Common Voice (Portuguese)

Portuguese
Beskikbaar Neutral

Default

English
Beskikbaar Neutral

MAI (Polish)

Polish
Beskikbaar Female

MAI (Ukrainian)

Ukrainian
Beskikbaar Neutral

VITS TTS ← FAQ

VITS means Variational Inference with adversarial learning for end-to-end Text-to-Speech. It generates audio in a single parallel pass using a variational autoencoder, normalizing flows, and adversarial (GAN) training, rather than a two-stage pipeline.

Yes. VITS is MIT-licensed and in the free tier, so it can be used commercially.

On TTS.ai, VITS covers 11 languages including English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, and Polish, with multi-speaker support. It does not do voice cloning.
← Alle stemme