VITS TTS
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
Incluír o texto en etiquetas SSML para un control preciso:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Etiquetas que o modelo escollido entende - prema para deixar unha no texto onde ocorre:
Este modelo le texto simple, polo que se ignoran as etiquetas inline. Para emocións baseadas en etiquetas, cambie a un modelo expresivo como Orpheus ou Bark.
Definir pronunciacións personalizadas (palabra = pronunciación):
Acerca de 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.
Mellor para: General-purpose text-to-speech with natural prosody
Examinar todo VITS vocesDe un vistazo
- Desenvolvente
- Jaehyeon Kim et al.
- Licenza
- MIT
- Tier
- free
- Velocidade
- fast
- Clonaxe de voz
- Non
- Linguas
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- Caracteres máximos
- 2000