Bark

Bark TTS

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

Enskri Limit pou 5,000 karaktè

Wrap ou tèks nan SSML tags pou presizyon kontwòl:

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

Tags ke modèl la chwazi konprann — klike pou mete yon nan tèks ou kote li rive:

Modèl sa a li tèks senp, se poutèt sa atik ki nan liy yo pa pran an kont. Pou efè ki baze sou atik, chanje pou yon modèl ekspresyon tankou Orpheus oswa Bark.

Define prononciations Custom (mot = prononciation):

-12 +12
0.5x 2.0x
Gratis ak Piper, VITS, MeloTTS
Son ou kreye a ap parèt isit la. Chwazi yon modèl, antre tèks la, epi klike Kreye.
Audio Generated Successfully
0:00
Telechaje son Telechaje.srt Link expires in 24h
Free tier: itilize pèsonèl. Lisans Komèsyal soti nan $5/mo
Love TTS.ai? Di zanmi ou yo!

Atik 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.

Pi bon pou: Creative audio content, audiobooks with emotion, sound effects

Navigue tout Bark Voy

Yon ti gade

Pwogramè
Suno
Lisans
MIT
Nivo
standard
Vitès
slow
Klonaj vwa
Non
Lang
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Karakteris maksimòm
200

Bark Voy

Chinese Speaker 1

Chinese
Standart Neutral

Chinese Speaker 2

Chinese
Standart Neutral

English Female 1

English
Standart Female

English Female 2

English
Standart Female

English Female 3

English
Standart Female

English Female 4

English
Standart Female

English Male 1

English
Standart Male

English Male 2

English
Standart Male

English Male 3

English
Standart Male

English Male 4

English
Standart Male

English Male 5

English
Standart Male

English Male 6

English
Standart Male

French Speaker 1

French
Standart Neutral

French Speaker 2

French
Standart Neutral

German Speaker 1

German
Standart Neutral

German Speaker 2

German
Standart Neutral

Hindi Speaker 1

Hindi
Standart Neutral

Italian Speaker 1

Italian
Standart Neutral

Japanese Speaker 1

Japanese
Standart Neutral

Japanese Speaker 2

Japanese
Standart Neutral

Korean Speaker 1

Korean
Standart Neutral

Korean Speaker 2

Korean
Standart Neutral

Polish Speaker 1

Polish
Standart Neutral

Portuguese Speaker 1

Portuguese
Standart Neutral

Russian Speaker 1

Russian
Standart Neutral

Spanish Speaker 1

Spanish
Standart Neutral

Spanish Speaker 2

Spanish
Standart Neutral

Turkish Speaker 1

Turkish
Standart 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.
← Tout vwa