Kokoro

Kokoro TTS

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

Melden Sie sich an für 5.000 Zeichen-Grenze

Verpacken Sie Ihren Text in SSML-Tags für eine präzise Kontrolle:

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

Tags, die das ausgewählte Modell versteht — klicken Sie, um einen in Ihren Text zu legen, wo es passiert:

Dieses Modell liest Text, so dass Inline-Tags ignoriert werden. Für tag-basierte Emotion, wechseln Sie zu einem ausdrucksstarken Modell wie Orpheus oder Bark.

Benutzerdefinierte Aussprachen definieren (Wort = Aussprache):

-12 +12
0.5x 2.0x
Frei mit Piper, VITS, MeloTTS
Hier erscheint Ihr generiertes Audio. Wählen Sie ein Modell, geben Sie Text ein und klicken Sie auf Generieren.
Audio-Erzeugung erfolgreich
0:00
Audio herunterladen Download.srt Link läuft in 24h aus
Freier Dienstgrad: persönlicher Gebrauch. Kommerzielle Lizenz ab $5/mo
Gefällt dir TTS.ai? Erzähl es deinen Freunden!

Über 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.

Das Beste für: High-quality TTS with minimal latency, streaming applications

Alle durchsuchen Kokoro Stimmen

Auf einen Blick

Entwickler
Hexgrad
Lizenz
Apache 2.0
Tierart
free
Geschwindigkeit
fast
Klonen der Stimme
Nein
Sprachen
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Maximale Zeichen
500

Kokoro Stimmen

Adam

English
Frei Male

Alex

Spanish
Frei Male

Alex

Portuguese
Frei Male

Alpha

Japanese
Frei Female

Alpha

Hindi
Frei Female

Bella

English
Frei Female

Dora

Portuguese
Frei Female

Dora

Spanish
Frei Female

Emma (British)

English
Frei Female

George (British)

English
Frei Male

Gongitsune

Japanese
Frei Female

Heart

English
Frei Female

Isabella (British)

English
Frei Female

Lewis (British)

English
Frei Male

Michael

English
Frei Male

Nicola

Italian
Frei Male

Nicole

English
Frei Female

Omega

Hindi
Frei Male

Sara

Italian
Frei Female

Sarah

English
Frei Female

Siwis

French
Frei Female

Sky

English
Frei Female

Xiaobei

Chinese
Frei Female

Xiaoni

Chinese
Frei Female

Xiaoxiao

Chinese
Frei Female

Yunjian

Chinese
Frei 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.
← Alle Stimmen