Oznake odabrani model razumije — kliknite da bacite jedan u vaš tekst gdje se to događa:
Ovaj model čita običan tekst, tako da inline oznake se zanemaruju. Za tag-based emocije, prebaci na ekspresivni model kao što su Orfeus ili Bark.
Prirodno-jezični znakovi isporuke. Počašćeni od Qwen3-TTS danas; drugi ekspresivni modeli dolaze uskoro.
Ovaj model ne podržava upute o stilu — prebaci se na model koji radi (npr. Qwen3-TTS).
Definiši vlastite izgovore (riječ = izgovor):
-12
+12
Kontrola ekspresnosti (0 = neutralna, 1 = vrlo ekspresna)
Težina smjera bez klasifikacije (viša = više brza praćenja)
Opišite glasovni stil na prirodnom jeziku (parler koristi ovo umjesto predefiniranih glasova)
Dia dijaloški format: Koristi [S1] i [S2] oznake za različite zvučnike. Primjerice: [S1] Pozdrav tamo! [S2] Zdravo, kako ste?
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.
Najbolje za: High-quality TTS with minimal latency, streaming applications
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Maks. znakova
500
Kokoro glasovi
Adam
English
SlobodnoMale
Alex
Spanish
SlobodnoMale
Alex
Portuguese
SlobodnoMale
Alpha
Hindi
SlobodnoFemale
Alpha
Japanese
SlobodnoFemale
Bella
English
SlobodnoFemale
Dora
Spanish
SlobodnoFemale
Dora
Portuguese
SlobodnoFemale
Emma (British)
English
SlobodnoFemale
George (British)
English
SlobodnoMale
Gongitsune
Japanese
SlobodnoFemale
Heart
English
SlobodnoFemale
Isabella (British)
English
SlobodnoFemale
Lewis (British)
English
SlobodnoMale
Michael
English
SlobodnoMale
Nicola
Italian
SlobodnoMale
Nicole
English
SlobodnoFemale
Omega
Hindi
SlobodnoMale
Sara
Italian
SlobodnoFemale
Sarah
English
SlobodnoFemale
Siwis
French
SlobodnoFemale
Sky
English
SlobodnoFemale
Xiaobei
Chinese
SlobodnoFemale
Xiaoni
Chinese
SlobodnoFemale
Xiaoxiao
Chinese
SlobodnoFemale
Yunjian
Chinese
SlobodnoMale
Kokoro TTS – FAQ
Kokoro is released under the Apache 2.0 license and sits in the free tier. On TTS.ai, audio you make with it is for personal use on the free tier and can be used commercially on any paid plan.
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.
