Bark

Bark TTS

Suno's transformer-based text-to-audio model that generates speech plus laughter, sighs, music, and sound effects.

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

Bark comes from Suno and takes a different approach from most TTS systems: it is a GPT-style transformer trained as a text-to-audio model rather than a pure text-to-speech one. Because it generates raw audio tokens, it can produce nonverbal sounds — laughing, sighing, crying — as well as background music and sound effects alongside the spoken words. It ships with 100+ speaker presets and handles 13+ languages including English, Chinese, French, German, Hindi, Japanese, and Korean. The trade-off is speed and length: at 350M parameters it runs slowly (~15s per clip) and caps at 200 characters, so it shines for short, emotive, creative audio rather than long narration.

Lo mejor para: Creative audio content, audiobooks with emotion, sound effects

Examinar todo Bark voces

De un vistazo

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

Bark voces

Chinese Speaker 1

Chinese
Estándar Neutral

Chinese Speaker 2

Chinese
Estándar Neutral

English Female 1

English
Estándar Female

English Female 2

English
Estándar Female

English Female 3

English
Estándar Female

English Female 4

English
Estándar Female

English Male 1

English
Estándar Male

English Male 2

English
Estándar Male

English Male 3

English
Estándar Male

English Male 4

English
Estándar Male

English Male 5

English
Estándar Male

English Male 6

English
Estándar Male

French Speaker 1

French
Estándar Neutral

French Speaker 2

French
Estándar Neutral

German Speaker 1

German
Estándar Neutral

German Speaker 2

German
Estándar Neutral

Hindi Speaker 1

Hindi
Estándar Neutral

Italian Speaker 1

Italian
Estándar Neutral

Japanese Speaker 1

Japanese
Estándar Neutral

Japanese Speaker 2

Japanese
Estándar Neutral

Korean Speaker 1

Korean
Estándar Neutral

Korean Speaker 2

Korean
Estándar Neutral

Polish Speaker 1

Polish
Estándar Neutral

Portuguese Speaker 1

Portuguese
Estándar Neutral

Russian Speaker 1

Russian
Estándar Neutral

Spanish Speaker 1

Spanish
Estándar Neutral

Spanish Speaker 2

Spanish
Estándar Neutral

Turkish Speaker 1

Turkish
Estándar Neutral

Bark TTS — Preguntas más frecuentes

Yes. Bark is a text-to-audio model, so beyond speech it can generate nonverbal cues like laughing, sighing and crying, plus music and background sound effects — one of its defining capabilities.

Yes. Bark is MIT-licensed, which permits commercial use.

Bark caps at 200 characters per request and is on the slower side (around 15 seconds per clip), so it is best suited to short, expressive snippets rather than long-form audio. It does not support voice cloning.
← Todas las voces