VITS

VITS TTS

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

Ku soo biir 5,000 xaraf xaddid

Wrap qoraalka ku SSML tags si loo hubiyo xakamaynta saxda ah:

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

Tags qaabka la doortay fahmo — riix si aad u hoos mid ka mid ah qoraalka aad halkaas oo uu ka dhacaa:

Model this akhriyo qoraalka caadiga ah, sidaas inline tags waa la iska indho tiri. For tag-ku salaysan dareenka, u dhaqaaqo si ay u muujiyaan qaabka sida Orpheus ama Bark.

Define custom pronunciations (word = dhawaaqa):

-12 +12
0.5x 2.0x
Bilaash ah oo leh Piper, VITS, MeloTTS
Your audio soo saaro halkan ka muuqan doonaa. Dooro qaab, ku qor qoraalka, oo guji soo saaro.
Dhaqdhaqaaqa ayaa la soo saaray
0:00
Soo dejisa Soo dejisan.srt Xidhiidhku wuxuu dhamaaday 24h
Free tier: isticmaalka shakhsiga ah. Liisan ganacsi laga bilaabo $ 5 / mo
Jecel TTS.ai? Ka warran saaxiibadaa!

About 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.

Ugu Fiican: General-purpose text-to-speech with natural prosody

Taabo oo kala soo bax VITS cod

Eeg

Soo-saarayaasha
Jaehyeon Kim et al.
Liisan
MIT
Qiyaamaha
free
Xawaaraha
fast
Duubista Codka
Ha
Afaf
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Noocyada ugu badan
2000

VITS cod

CSS10 (Dutch)

Dutch
Bilaash Neutral

CSS10 (Finnish)

Finnish
Bilaash Neutral

CSS10 (French)

French
Bilaash Neutral

CSS10 (German)

German
Bilaash Neutral

CSS10 (Hungarian)

Hungarian
Bilaash Neutral

CSS10 (Spanish)

Spanish
Bilaash Neutral

Common Voice (Bulgarian)

Bulgarian
Bilaash Neutral

Common Voice (Portuguese)

Portuguese
Bilaash Neutral

Default

English
Bilaash Neutral

MAI (Polish)

Polish
Bilaash Female

MAI (Ukrainian)

Ukrainian
Bilaash Neutral

VITS Su'aalaha La Weydiiyo

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.
← Codadka oo dhan