Kokoro

Kokoro TTS

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

Inscrivez-vous pour la limite de 5 000 caractères

Enveloppez votre texte dans des balises SSML pour un contrôle précis :

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

Mots clés le modèle sélectionné comprend — cliquez pour en déposer un dans votre texte où il se produit:

Ce modèle lit du texte clair, donc les balises en ligne sont ignorées. Pour l'émotion basée sur les tags, passer à un modèle expressif comme Orphée ou Bark.

Définir les prononciations personnalisées (mot = prononciation) :

-12 +12
0.5x 2.0x
Gratuit avec Piper, VITS, MeloTTS
Votre audio généré apparaîtra ici. Choisissez un modèle, entrez le texte et cliquez sur Générer.
Production audio réussie
0:00
Télécharger l'audio Télécharger.srt Lien expire en 24h
Niveau gratuit: usage personnel. Licence commerciale à partir de 5 $/mois
Vous aimez TTS.ai ? Parlez-en à vos amis !

À propos 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.

Meilleur pour: High-quality TTS with minimal latency, streaming applications

Tout voir Kokoro voix

En un coup d'oeil

Développeur
Hexgrad
Licence
Apache 2.0
Niveau
free
Régime
fast
Closonnage de la voix
Numéro
Langues
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Personnages maxi
500

Kokoro voix

Adam

English
Gratuit Male

Alex

Spanish
Gratuit Male

Alex

Portuguese
Gratuit Male

Alpha

Japanese
Gratuit Female

Alpha

Hindi
Gratuit Female

Bella

English
Gratuit Female

Dora

Portuguese
Gratuit Female

Dora

Spanish
Gratuit Female

Emma (British)

English
Gratuit Female

George (British)

English
Gratuit Male

Gongitsune

Japanese
Gratuit Female

Heart

English
Gratuit Female

Isabella (British)

English
Gratuit Female

Lewis (British)

English
Gratuit Male

Michael

English
Gratuit Male

Nicola

Italian
Gratuit Male

Nicole

English
Gratuit Female

Omega

Hindi
Gratuit Male

Sara

Italian
Gratuit Female

Sarah

English
Gratuit Female

Siwis

French
Gratuit Female

Sky

English
Gratuit Female

Xiaobei

Chinese
Gratuit Female

Xiaoni

Chinese
Gratuit Female

Xiaoxiao

Chinese
Gratuit Female

Yunjian

Chinese
Gratuit Male

Kokoro TTS — FAQ

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.
← Toutes les voix