VITS 음성 인식
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
정확한 제어를 위해 SSML 태그로 텍스트를 래핑하십시오.
<speak><prosody rate="slow">Slow speech</prosody></speak>
선택한 모델이 이해하는 태그 — 텍스트에 드래그하려면 클릭하세요:
이 모델은 일반 텍스트를 읽기 때문에 인라인 태그는 무시됩니다. 태그 기반 감정을 위해서는 Orpheus 또는 Bark과 같은 표현 모델로 전환하십시오.
사용자 지정 발음 정의 (단어 = 발음):
정보 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.
최적화된 용도: General-purpose text-to-speech with natural prosody
모두 찾아보기 VITS 목소리한눈에
- 개발자
- Jaehyeon Kim et al.
- 라이선스
- MIT
- 종
- free
- 속도
- fast
- 음성 복제
- 아니요
- 언어
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- 최대 문자수
- 2000