VITS

VITS TTS

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

Ṣẹ̀dà fun àwọn àmì-àṣírí 5,000

Fi àkọlé rẹ pamọ́ sí àwọn àmì-ìwé SSML fún ìdáràn:

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

Àwọn Àmì-ìwé tí àwọn ìṣàmúlò-ètò tí a yàn gbọ́ - tẹ̀ láti fi ọkan sínú àkọ́lé rẹ̀ nínú àwọn ààyè-iṣẹ́ tí o bá jẹ́:

Àwọn àwọn àkọlé àwọn ààyè-iṣẹ́ àwọn àwọn àmì-ìwé àwọn àmì-ìwé àwọn àwọn àmì-ìwé àwọn à

Àwọn àwọn ìṣàfarawé àwọn àwọn ìṣàfarawé àwọn (ọrọ = ìṣàfàlì):

-12 +12
0.5x 2.0x
Free pẹlu Piper, VITS, MeloTTS
Àwọn àwòrán tí o ti ṣẹ̀dà tí o bá han níbẹ̀. Yan àwọn àwòrán, tẹ̀lẹ̀ àkọlé, ki o si tẹ̀ Ṣẹ̀dà.
Àwọn àwọn àwòrán tí a ṣẹ̀dà
0:00
Ṣàfikún Àwọn Àmì-ìwé Ṣàfikún.srt Líǹkì náà kù nínú 24h
Ìjádé ọ̀fẹ́: ìlòjútó ara ẹni. Lisensi Iṣowo ori lati $5/mo
O fẹ́ TTS.ai? Fì sọ̀kalẹ̀ fún àwọn ọrẹ̀ rẹ̀!

Ààyè-iṣẹ́ 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.

Tí o dara jù fún: General-purpose text-to-speech with natural prosody

Wá Gbogbo àwòrán VITS Àwọn àwòrán

Nínú àwọn ìṣàfarawé

Àwọn Àkọlé
Jaehyeon Kim et al.
Àwọn Ààyè-iṣẹ́
MIT
Àwọn àwọn ààyè-iṣẹ́
free
Ìjánu-ìṣàmúlò-ètò
fast
Ìṣàfarawé àwọn àmì-ìwé
Àwọn àwọn àgbéwọlé
Àwọn
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Àwọn àyọkà ìpele
2000

VITS Àwọn àwòrán

CSS10 (Dutch)

Dutch
Àìfẹ́ Neutral

CSS10 (Finnish)

Finnish
Àìfẹ́ Neutral

CSS10 (French)

French
Àìfẹ́ Neutral

CSS10 (German)

German
Àìfẹ́ Neutral

CSS10 (Hungarian)

Hungarian
Àìfẹ́ Neutral

CSS10 (Spanish)

Spanish
Àìfẹ́ Neutral

Common Voice (Bulgarian)

Bulgarian
Àìfẹ́ Neutral

Common Voice (Portuguese)

Portuguese
Àìfẹ́ Neutral

Default

English
Àìfẹ́ Neutral

MAI (Polish)

Polish
Àìfẹ́ Female

MAI (Ukrainian)

Ukrainian
Àìfẹ́ Neutral

VITS Àwọn Àtòjọ-ẹ̀yàn

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.
← Gbogbo àwọn ìrànwọ́