Bark

Bark TTS

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

Inscríbete límite de 5. 000 caracteres

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):

-12 +12
0.5x 2.0x
Libre con Piper, VITS, MeloTTS
O son xerado aparecerá aquí. Escolla un modelo, introduza o texto e prema Xerar.
O son xerou correctamente
0:00
Obter o son Obter.srt A ligazón caduca en 24 horas
Nivel libre: uso persoal. Licenza comercial desde $5/mes
Encántalle TTS.ai? Cóntallo aos teus 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.

Mellor para: Creative audio content, audiobooks with emotion, sound effects

Examinar todo Bark voces

De un vistazo

Desenvolvente
Suno
Licenza
MIT
Tier
standard
Velocidade
slow
Clonaxe de voz
Non
Linguas
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Caracteres máximos
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 - FAQ

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 as voces