VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Nglapisi teks ing tag SSML kanggo kontrol sing tepat:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tag kang dipahami model kang dipilih — klik kanggo ngethok siji menyang teks sampeyan ing ngendi iku kedadeyan:
Model ieu maca teks biasa, jadi tag inline diabaikan. Pikeun emosi dumasar tag, ganti ka model ekspresif kayaning Orpheus atawa Bark.
Nyathet pangucapan standar (kata = pangucapan):
About 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.
Paling apik kanggo: General-purpose text-to-speech with natural prosody
Nglayar kabeh VITS suaraIng cetha
- Pangembang
- Jaehyeon Kim et al.
- Lisensi
- MIT
- Tingkat
- free
- Kecepatan
- fast
- Kloning suara
- Ora
- Basa
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Karakter paling akeh
- 2000