Kokoro

Kokoro TTS

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

Cláraigh anois! le haghaidh teorainn 5,000 carachtar

Cuir do théacs i gclibeanna SSML le haghaidh rialú beacht:

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

Clibeanna a thuigeann an tsamhail roghnaithe — cliceáil chun ceann a scaoileadh isteach i do théacs nuair a tharlaíonn sé:

Léann an tsamhail seo gnáth- théacs, mar sin déantar neamhaird ar chlibeanna inlíne. Chun mothúchán clibbhunaithe a chruthú, athraigh go samhail léiritheach cosúil le Orpheus nó Bark.

Sainmhínigh fuaimniú saincheaptha (focal = fuaimniú):

-12 +12
0.5x 2.0x
Saor in Aisce le Piper, VITS, MeloTTS
Taispeánfar an fhuaim a ghintear anseo. Roghnaigh samhail, iontráil téacs, agus cliceáil Giniúint.
D' éirigh le giniúint na fuaime
0:00
Íosluchtaigh Fuaim Íoslódáil.srt Téann an nasc in éag i 24h
Ciseal saor in aisce: úsáid phearsanta. Ceadúnas Tráchtála ó $ 5 / mo
Leabaigh an Tweet Ag tabhairt freagra ar friends!

Eolas Faoi 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.

Is Fearr le haghaidh: High-quality TTS with minimal latency, streaming applications

Brabhsáil Uile Kokoro guthanna

Ag Sracfhéachaint

Forbróir
Hexgrad
Ceadúnas
Apache 2.0
Tír
free
Luas
fast
Clónáil gutha
& Ná Sábháil
Teangacha
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Carachtair Uasta
500

Kokoro guthanna

Adam

English
Saor Male

Alex

Spanish
Saor Male

Alex

Portuguese
Saor Male

Alpha

Japanese
Saor Female

Alpha

Hindi
Saor Female

Bella

English
Saor Female

Dora

Portuguese
Saor Female

Dora

Spanish
Saor Female

Emma (British)

English
Saor Female

George (British)

English
Saor Male

Gongitsune

Japanese
Saor Female

Heart

English
Saor Female

Isabella (British)

English
Saor Female

Lewis (British)

English
Saor Male

Michael

English
Saor Male

Nicola

Italian
Saor Male

Nicole

English
Saor Female

Omega

Hindi
Saor Male

Sara

Italian
Saor Female

Sarah

English
Saor Female

Siwis

French
Saor Female

Sky

English
Saor Female

Xiaobei

Chinese
Saor Female

Xiaoni

Chinese
Saor Female

Xiaoxiao

Chinese
Saor Female

Yunjian

Chinese
Saor Male

Kokoro TTS - Ceisteanna Coitianta

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.
← Gach guth