VITS

VITS TTS

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

Irreġistra issa għal 5,000 karattru limitu

Wrap test tiegħek fil-tags SSML għall-kontroll preċiż:

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

Tags li l-mudell magħżul jifhem — ikklikkja biex tqiegħed waħda fit-test tiegħek fejn jiġri:

Dan il-mudell jaqra test sempliċi, għalhekk it-tags inline huma injorati.Għal emozzjoni bbażata fuq it-tag, aqleb għal mudell espressiv bħal Orpheus jew Bark.

Iddefinixxi pronunzji tad-dwana (kelma = pronunzja):

-12 +12
0.5x 2.0x
Ħieles ma Piper, VITS, MeloTTS
L-awdjo iġġenerat tiegħek se jidher hawnhekk. Agħżel mudell, daħħal it-test, u kklikkja Iġġenera.
Awdjo Iġġenerat b'suċċess
0:00
Niżżel l-awdjo Niżżel.srt Il-link tiskadi f'24 siegħa
Livell Ħieles: użu personali. Liċenzja Kummerċjali minn $5/mo
Agħmel dan il-vuċi tiegħek stess Klona vuċi f'30 sekonda
Imħabba TTS.ai? Għid lill-ħbieb tiegħek!

Dwar 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.

L-aħjar għal: General-purpose text-to-speech with natural prosody

Ibbrawżja kollox VITS vuċijiet

Daqqa t'għajn

Żviluppatur
Jaehyeon Kim et al.
Liċenzja
MIT
Annimali
free
Veloċità
fast
Klonazzjoni tal-vuċi
Nru
Lingwi
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Karattri massimi
2000

VITS vuċijiet

CSS10 (Dutch)

Dutch
Ħieles Neutral

CSS10 (Finnish)

Finnish
Ħieles Neutral

CSS10 (French)

French
Ħieles Neutral

CSS10 (German)

German
Ħieles Neutral

CSS10 (Hungarian)

Hungarian
Ħieles Neutral

CSS10 (Spanish)

Spanish
Ħieles Neutral

Common Voice (Bulgarian)

Bulgarian
Ħieles Neutral

Common Voice (Portuguese)

Portuguese
Ħieles Neutral

Default

English
Ħieles Neutral

MAI (Polish)

Polish
Ħieles Female

MAI (Ukrainian)

Ukrainian
Ħieles Neutral

VITS TTS — Mistoqsijiet Frekwenti

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.
← Il-vuċijiet kollha