GPT-SoVITS

GPT-SoVITS TTS

A few-shot voice cloning model that replicates a voice — and can even sing — from as little as five seconds of audio.

Inscríbete para el límite de 5.000 caracteres

Envuelva su texto en etiquetas SSML para un control preciso:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Etiquetas el modelo seleccionado entiende — haga clic para soltar uno en su texto donde sucede:

Este modelo lee texto plano, por lo que las etiquetas en línea son ignoradas. Para la emoción basada en etiquetas, cambie a un modelo expresivo como Orfeo o Bark.

Definir pronunciaciones personalizadas (palabra = pronunciación):

-12 +12
0.5x 2.0x
Libre con Piper, VITS, MeloTTS
Su audio generado aparecerá aquí. Elija un modelo, introduzca texto y haga clic en Generar.
Audio generado con éxito
0:00
Descargar audio Descargar.srt Enlace expira en 24h
Nivel libre: uso personal. Licencia comercial desde $5/mes
Haz de esto tu propia voz Clonar una voz en 30 segundos
¿Te gusta TTS.ai? ¡Cuéntaselo a tus amigos!

Acerca de GPT-SoVITS

GPT-SoVITS, created by the developer known as RVC-Boss, combines GPT-style language modeling with SoVITS (Singing Voice Conversion / synthesis) to deliver some of the most accessible voice cloning in open source. With as little as five seconds of reference audio it captures a speaker's timbre and style, and it stands out from most TTS models in handling singing as well as speech. It works across English, Chinese, Japanese, and Korean and supports cross-lingual generation, so a cloned voice can speak a language the reference clip never used. It is widely used by content creators for voice replication, dubbing, and song covers, and reaches high fidelity for a model of its size.

Lo mejor para: Voice cloning, singing synthesis, content creator voice replication

Examinar todo GPT-SoVITS voces

De un vistazo

Desarrollador
RVC-Boss
Licencia
MIT
Nivel
standard
Velocidad
slow
Clonación de voz
Idiomas
English, Chinese, Japanese, Korean
Máx. caracteres
500

GPT-SoVITS voces

Default

Chinese
Estándar Neutral

English Default

English
Estándar Neutral

Japanese Default

Japanese
Estándar Neutral

Korean Default

Korean
Estándar Neutral

GPT-SoVITS TTS — Preguntas más frecuentes

As little as five seconds. It uses few-shot learning, so a short reference clip is enough to capture a speaker, though a cleaner and slightly longer sample improves similarity.

Yes. Its SoVITS lineage comes from singing voice synthesis, so unlike most TTS models it can generate singing as well as spoken voice, which is why it is popular for song covers.

English, Chinese, Japanese, and Korean, with cross-lingual synthesis — a voice cloned from one language can be made to speak the others.
← Todas las voces