Kokoro

Kokoro TTS

An 82M-parameter open model from Hexgrad that delivers studio-quality speech at nearly 100x real-time.

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 Kokoro

Kokoro, built by Hexgrad, is a deliberately tiny 82-million-parameter model that punches far above its size class. It uses a StyleTTS + ISTFTNet architecture and was trained on roughly 1,200 hours of speech, yet generates audio close to 100x faster than real-time on a GPU while staying remarkably natural and expressive. It covers English, Japanese, Chinese, French, Italian, Portuguese, Spanish, and Hindi with a varied set of expressive voicepacks, and supports streaming. The combination of small footprint, low latency, and a permissive license has made Kokoro one of the most popular free models for high-volume and streaming use — it carries the largest share of traffic on TTS.ai.

Tí o dara jù fún: High-quality TTS with minimal latency, streaming applications

Wá Gbogbo àwòrán Kokoro Àwọn àwòrán

Nínú àwọn ìṣàfarawé

Àwọn Àkọlé
Hexgrad
Àwọn Ààyè-iṣẹ́
Apache 2.0
Àwọn àwọn ààyè-iṣẹ́
free
Ìjánu-ìṣàmúlò-ètò
fast
Ìṣàfarawé àwọn àmì-ìwé
Àwọn àwọn àgbéwọlé
Àwọn
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Àwọn àyọkà ìpele
500

Kokoro Àwọn àwòrán

Adam

English
Àìfẹ́ Male

Alex

Spanish
Àìfẹ́ Male

Alex

Portuguese
Àìfẹ́ Male

Alpha

Japanese
Àìfẹ́ Female

Alpha

Hindi
Àìfẹ́ Female

Bella

English
Àìfẹ́ Female

Dora

Portuguese
Àìfẹ́ Female

Dora

Spanish
Àìfẹ́ Female

Emma (British)

English
Àìfẹ́ Female

George (British)

English
Àìfẹ́ Male

Gongitsune

Japanese
Àìfẹ́ Female

Heart

English
Àìfẹ́ Female

Isabella (British)

English
Àìfẹ́ Female

Lewis (British)

English
Àìfẹ́ Male

Michael

English
Àìfẹ́ Male

Nicola

Italian
Àìfẹ́ Male

Nicole

English
Àìfẹ́ Female

Omega

Hindi
Àìfẹ́ Male

Sara

Italian
Àìfẹ́ Female

Sarah

English
Àìfẹ́ Female

Siwis

French
Àìfẹ́ Female

Sky

English
Àìfẹ́ Female

Xiaobei

Chinese
Àìfẹ́ Female

Xiaoni

Chinese
Àìfẹ́ Female

Xiaoxiao

Chinese
Àìfẹ́ Female

Yunjian

Chinese
Àìfẹ́ Male

Kokoro Àwọn Àtòjọ-ẹ̀yàn

Yes. Kokoro is released under the Apache 2.0 license and sits in the free tier, so it can be used commercially at no cost.

Kokoro is only 82M parameters and uses an efficient StyleTTS + ISTFTNet design, letting it generate audio nearly 100x faster than real-time on a GPU with just ~1.5GB VRAM while staying natural-sounding.

Kokoro supports English, Japanese, Chinese, French, Italian, Portuguese, Spanish, and Hindi, each with its own expressive voicepacks. It does not support voice cloning.
← Gbogbo àwọn ìrànwọ́