VITS

VITS TTS

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

Ojejapo 5000 caracter rehegua límite

Ojehaijey ñe'ẽnguéra etiquetas SSML-pe peteĩ control hekopete g̃uarã:

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

Etiquetas ohechakuaáva modelo ojeporavóva - tesãirã peteĩ peteĩva ñe'ẽnguérape, oĩhápe:

Ko modelo ohai texto ndahasyivéva, upévare umi etiqueta oĩva línea ryepýpe ndojehechakuaái. Umi emoción oñemopyendáva etiqueta-pe g̃uarã, oñemoambue peteĩ modelo expresivo-pe taha'e Orfeo térã Bark.

Oñemohenda ñe'ẽnguéra ojehechapyréva (tembiapo = ñe'ẽnguéra):

-12 +12
0.5x 2.0x
Libre Piper, VITS, MeloTTS ndive
Audio-kuéra oguenohẽva ojekuaauka ko'ápe. Oñeporavo peteĩ modelo, omoĩnge ñe'ẽ ha ohesa'ỹijo Generar.
Audio oñemoheñói porã
0:00
Oñeguenohẽ marandu myambue guive Oñeguenohẽ.srt Ko enlace hi'are 24 h rire
Nivel libre: jeiporu personal. Licencia comercial $5/ha'e rupi
Ehayhuetéva TTS.ai? He'i umi iñangirũpe!

Mba'épa 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.

Oñeha'ãvéva: General-purpose text-to-speech with natural prosody

Ojehecha opavave VITS ñe'ẽ

Peteĩ jehecha

Desarrollador
Jaehyeon Kim et al.
Licencia
MIT
Ta'ãnga
free
Velocidad
fast
Clonación ñe'ẽnguéra rehe
No
Ñe'ẽ
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Caracteres máx.
2000

VITS ñe'ẽ

CSS10 (Dutch)

Dutch
Libre Neutral

CSS10 (Finnish)

Finnish
Libre Neutral

CSS10 (French)

French
Libre Neutral

CSS10 (German)

German
Libre Neutral

CSS10 (Hungarian)

Hungarian
Libre Neutral

CSS10 (Spanish)

Spanish
Libre Neutral

Common Voice (Bulgarian)

Bulgarian
Libre Neutral

Common Voice (Portuguese)

Portuguese
Libre Neutral

Default

English
Libre Neutral

MAI (Polish)

Polish
Libre Female

MAI (Ukrainian)

Ukrainian
Libre Neutral

VITS Pregunta ojehechavéva

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.
← Opaite ñe'ẽ