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.

Ṣẹ̀dà fun àwọn àmì-àṣírí 5,000

Fi àkọlé rẹ pamọ́ sí àwọn àmì-ìwé SSML fún ìdáràn:

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

Àwọn Àmì-ìwé tí àwọn ìṣàmúlò-ètò tí a yàn gbọ́ - tẹ̀ láti fi ọkan sínú àkọ́lé rẹ̀ nínú àwọn ààyè-iṣẹ́ tí o bá jẹ́:

Àwọn àwọn àkọlé àwọn ààyè-iṣẹ́ àwọn àwọn àmì-ìwé àwọn àmì-ìwé àwọn àwọn àmì-ìwé àwọn à

Àwọn àwọn ìṣàfarawé àwọn àwọn ìṣàfarawé àwọn (ọrọ = ìṣàfàlì):

-12 +12
0.5x 2.0x
Free pẹlu Piper, VITS, MeloTTS
Àwọn àwòrán tí o ti ṣẹ̀dà tí o bá han níbẹ̀. Yan àwọn àwòrán, tẹ̀lẹ̀ àkọlé, ki o si tẹ̀ Ṣẹ̀dà.
Àwọn àwọn àwòrán tí a ṣẹ̀dà
0:00
Ṣàfikún Àwọn Àmì-ìwé Ṣàfikún.srt Líǹkì náà kù nínú 24h
Ìjádé ọ̀fẹ́: ìlòjútó ara ẹni. Lisensi Iṣowo ori lati $5/mo
O fẹ́ TTS.ai? Fì sọ̀kalẹ̀ fún àwọn ọrẹ̀ rẹ̀!

Ààyè-iṣẹ́ 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.

Tí o dara jù fún: Quick creative audio when full Bark is too slow

Wá Gbogbo àwòrán Bark Small Àwọn àwòrán

Nínú àwọn ìṣàfarawé

Àwọn Àkọlé
Suno
Àwọn Ààyè-iṣẹ́
MIT
Àwọn àwọn ààyè-iṣẹ́
standard
Ìjánu-ìṣàmúlò-ètò
medium
Ìṣàfarawé àwọn àmì-ìwé
Àwọn àwọn àgbéwọlé
Àwọn
English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
Àwọn àyọkà ìpele
200

Bark Small Àwọn àwòrán

Chinese Speaker

Chinese
Àwọn ìpéwọ̀n Neutral

English Female 1

English
Àwọn ìpéwọ̀n Female

English Female 2

English
Àwọn ìpéwọ̀n Female

English Male 1

English
Àwọn ìpéwọ̀n Male

French Speaker

French
Àwọn ìpéwọ̀n Neutral

German Speaker

German
Àwọn ìpéwọ̀n Neutral

Hindi Speaker

Hindi
Àwọn ìpéwọ̀n Neutral

Italian Speaker

Italian
Àwọn ìpéwọ̀n Neutral

Japanese Speaker

Japanese
Àwọn ìpéwọ̀n Neutral

Korean Speaker

Korean
Àwọn ìpéwọ̀n Neutral

Polish Speaker

Polish
Àwọn ìpéwọ̀n Neutral

Portuguese Speaker

Portuguese
Àwọn ìpéwọ̀n Neutral

Russian Speaker

Russian
Àwọn ìpéwọ̀n Neutral

Spanish Speaker

Spanish
Àwọn ìpéwọ̀n Neutral

Turkish Speaker

Turkish
Àwọn ìpéwọ̀n Neutral

Bark Small Àwọn Àtòjọ-ẹ̀yàn

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.
← Gbogbo àwọn ìrànwọ́