Bark Small

Bark Small TTS

A distilled 150M version of Suno's Bark that trades some fidelity for roughly twice the speed and half the memory.

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 Bark Small

Bark Small is Suno's distilled, lightweight take on Bark, shrinking the model to 150M parameters. It keeps Bark's signature ability to produce emotional speech, laughter, and multilingual output across the same 13+ languages, but generates noticeably faster (~8s versus ~15s) and fits in about 2GB of VRAM. The cost is some audio quality, so it works best as the go-to when full Bark is too slow for a creative task but you still want its expressive, sound-rich character. Like full Bark it caps at 200 characters per generation and does not support voice cloning.

Lo mejor para: Quick creative audio when full Bark is too slow

Examinar todo Bark Small voces

De un vistazo

Desarrollador
Suno
Licencia
MIT
Nivel
standard
Velocidad
medium
Clonación de voz
No
Idiomas
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Máx. caracteres
200

Bark Small voces

Chinese Speaker

Chinese
Estándar Neutral

English Female 1

English
Estándar Female

English Female 2

English
Estándar Female

English Male 1

English
Estándar Male

French Speaker

French
Estándar Neutral

German Speaker

German
Estándar Neutral

Hindi Speaker

Hindi
Estándar Neutral

Italian Speaker

Italian
Estándar Neutral

Japanese Speaker

Japanese
Estándar Neutral

Korean Speaker

Korean
Estándar Neutral

Polish Speaker

Polish
Estándar Neutral

Portuguese Speaker

Portuguese
Estándar Neutral

Russian Speaker

Russian
Estándar Neutral

Spanish Speaker

Spanish
Estándar Neutral

Turkish Speaker

Turkish
Estándar Neutral

Bark Small TTS — Preguntas más frecuentes

Bark Small is a distilled 150M-parameter version (versus 350M for full Bark). It runs faster — around 8 seconds per clip in ~2GB VRAM — at the cost of some audio quality, while keeping the same emotional and multilingual abilities.

Yes. Like full Bark, Bark Small is MIT-licensed and free for commercial use.

Choose Bark Small for quick, creative, emotive snippets when full Bark is too slow. Both share a 200-character cap, the same 13+ languages, and neither supports voice cloning.
← Todas las voces