VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Wrap wanu malemba mu SSML tags kwa kuwongolera moyenera:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags chosankhidwa chitsanzo amamvetsa - dinani kuti aphe mmodzi m'mawu anu pamene chimachitika:
Izi ndi njira yolemba malemba oyera, kotero ma tag ophatikizidwa amasiya kuganiziridwa. Kuti mupange ma tag ogwirizana ndi maganizo, gwiritsani ntchito njira yolemba malemba monga Orpheus kapena Bark.
Define custom pronunciations (word = pronunciation):
Za 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.
Best kwa: General-purpose text-to-speech with natural prosody
Pezani zonse VITS maganizoPa mphindi
- Wopanga
- Jaehyeon Kim et al.
- License
- MIT
- Mtundu
- free
- Kuyenda
- fast
- Kusintha kwa mawu
- Si
- Zilankhulo
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Max characters
- 2000