Bark

Bark TTS

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

Whakawhanake mō te tepe o ngā tohu 5,000

Whāriki i tōna kupu i roto i ngā tohu SSML mō te whakahaere tika:

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

E mōhio ana ngā tohu ki te tauira i kōwhiria - ka kōwhiria kia whakawātea tētahi ki roto i tōna kupu i reira ka puta ai:

Ka pānui tēnei tauira i te kupu noa, nā reira ka whakakāhoretia ngā tohu ā-waitara. Mō te āhua o te tohu-taihi, ka huri ki tētahi tauira whakamārama pēnei i a Orpheus, Bark rānei.

Ka tautuhia ngā tohutohu ā-ringa (wāhi = tohutohu):

-12 +12
0.5x 2.0x
Waihoki me Piper, VITS, MeloTTS
Ka puta tēnei te oro i waihangatia e koe. Ka kōwhiria tētahi tauira, ka tāurua te kupu, a, ka kōwhiria te Whakatū.
Kua angitu te whakaputanga oro
0:00
Waihoki i te oro Whakahua.srt Ka ngaro te pānga i roto i te 24h
Tauwhāinga wātea: te whakamahinga whaiaro. Whakawhiwhinga hokohoko mai i te $5/mo
E manakohia ana e TTS.ai? Whakapāpāho ki ōna hoa!

Mo 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.

Pai mo: Creative audio content, audiobooks with emotion, sound effects

Ka tirohia katoa Bark ngā oro

I te tirohanga

Ka whakawhanakehia
Suno
Ka taea te whakawātea
MIT
Karaka
standard
Āhuatanga
slow
Whakakōrero reo
Kāore
reo
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Kāri nui rawa
200

Bark ngā oro

Chinese Speaker 1

Chinese
Paerewa Neutral

Chinese Speaker 2

Chinese
Paerewa Neutral

English Female 1

English
Paerewa Female

English Female 2

English
Paerewa Female

English Female 3

English
Paerewa Female

English Female 4

English
Paerewa Female

English Male 1

English
Paerewa Male

English Male 2

English
Paerewa Male

English Male 3

English
Paerewa Male

English Male 4

English
Paerewa Male

English Male 5

English
Paerewa Male

English Male 6

English
Paerewa Male

French Speaker 1

French
Paerewa Neutral

French Speaker 2

French
Paerewa Neutral

German Speaker 1

German
Paerewa Neutral

German Speaker 2

German
Paerewa Neutral

Hindi Speaker 1

Hindi
Paerewa Neutral

Italian Speaker 1

Italian
Paerewa Neutral

Japanese Speaker 1

Japanese
Paerewa Neutral

Japanese Speaker 2

Japanese
Paerewa Neutral

Korean Speaker 1

Korean
Paerewa Neutral

Korean Speaker 2

Korean
Paerewa Neutral

Polish Speaker 1

Polish
Paerewa Neutral

Portuguese Speaker 1

Portuguese
Paerewa Neutral

Russian Speaker 1

Russian
Paerewa Neutral

Spanish Speaker 1

Spanish
Paerewa Neutral

Spanish Speaker 2

Spanish
Paerewa Neutral

Turkish Speaker 1

Turkish
Paerewa 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.
← Ko nga oro katoa