Kokoro

Kokoro TTS

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

Kugadzwa for 5,000 character limit

Wrap yako tenzi mu SSML tags kuti zvive nyore kudzora:

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

Tags iyo yakasarudzwa model inonzwisiswa — tinya kuti utore imwe muchinyorwa chako apo inoitika:

Iyi modhi inoverenga chete mazita ezvinyorwa, saka zvinyorwa zvinonyorwa mumitsara hazvina kutariswa. Kuti uwane pfungwa dziri mumitsara, chinja kune imwe modhi inoratidza pfungwa seOrpheus kana Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free with Piper, VITS, MeloTTS
Yako yakagadzirwa audio ichaonekwa pano. Choose a model, enter text, and click Generate.
Audio Yakagadzirwa Nekubudirira
0:00
Download Audio Dhawunirodha.srt Link inotanga kushanda mu 24h
Free tier: personal usage. Commercial license from $5/mo
Love TTS.ai? Tiudza shamwari dzako!

Chii 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.

Yakanaka kune: High-quality TTS with minimal latency, streaming applications

Tarisa zvese Kokoro mazwi

Mufananidzo

Developer
Hexgrad
License
Apache 2.0
Tier
free
Speed
fast
Kutaura
Hapana
Zvinhu
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Max characters
500

Kokoro mazwi

Adam

English
Free Male

Alex

Spanish
Free Male

Alex

Portuguese
Free Male

Alpha

Japanese
Free Female

Alpha

Hindi
Free Female

Bella

English
Free Female

Dora

Portuguese
Free Female

Dora

Spanish
Free Female

Emma (British)

English
Free Female

George (British)

English
Free Male

Gongitsune

Japanese
Free Female

Heart

English
Free Female

Isabella (British)

English
Free Female

Lewis (British)

English
Free Male

Michael

English
Free Male

Nicola

Italian
Free Male

Nicole

English
Free Female

Omega

Hindi
Free Male

Sara

Italian
Free Female

Sarah

English
Free Female

Siwis

French
Free Female

Sky

English
Free Female

Xiaobei

Chinese
Free Female

Xiaoni

Chinese
Free Female

Xiaoxiao

Chinese
Free Female

Yunjian

Chinese
Free Male

Kokoro TTS — Zvinyorwa

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.
← All voices