VITS

VITS TTS

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

Daftar untuk batas 5,000 karakter

Bungkus teks Anda dalam tag SSML untuk kendali yang tepat:

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

Tag yang dipilih mengerti klik °C untuk memasukkan satu ke dalam teks Anda di mana hal itu terjadi:

Model ini membaca teks biasa, sehingga tag inline diabaikan. Untuk tag berbasis emosi, beralih ke model ekspresif seperti Orpheus atau Bark.

Definisikan pengucapan ubahan (kata = pelafalan):

-12 +12
0.5x 2.0x
Free with Piper, VITS, Melotts
Audio yang Anda buat akan muncul di sini. Pilih model, masukkan teks, dan klik Generate.
Hasil Audio Berhasil
0:00
Unduh Audio Unduh.srt Sambungan berakhir dalam 24 jam
Tingkatan bebas: penggunaan pribadi. Ijin komersial dari $5/mo
Buatlah ini suara Anda sendiri Kloning suara dalam 30 detik
Beritahu teman-temanmu!

Tentang 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.

Terbaik untuk: General-purpose text-to-speech with natural prosody

Jelajahi semua VITS suara

Pada sekilas

Pengembang
Jaehyeon Kim et al.
Lisensi
MIT
Tier
free
Kecepatan
fast
Penklonan Suara
Tidak
Bahasa
English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
Karakter maksimal
2000

VITS suara

CSS10 (Dutch)

Dutch
Bebas Neutral

CSS10 (Finnish)

Finnish
Bebas Neutral

CSS10 (French)

French
Bebas Neutral

CSS10 (German)

German
Bebas Neutral

CSS10 (Hungarian)

Hungarian
Bebas Neutral

CSS10 (Spanish)

Spanish
Bebas Neutral

Common Voice (Bulgarian)

Bulgarian
Bebas Neutral

Common Voice (Portuguese)

Portuguese
Bebas Neutral

Default

English
Bebas Neutral

MAI (Polish)

Polish
Bebas Female

MAI (Ukrainian)

Ukrainian
Bebas Neutral

VITS TTS °F 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.
← Semua suara