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