Merker den valgte modellen forstår – klikk for å slippe en i teksten der den skjer:
Denne modellen leser ren tekst, så merker i teksten blir ignorert. Bytt til en ekspressiv modell som Orfeus eller Bark for å bruke tagger.
Leveringssignal for naturlig språk. Hedd av Qwen3- TTS i dag, andre ekspressive modeller kommer snart.
Denne modellen støtter ikke stilinstrukser – bytte til en modell som gjør det (f.eks. Qwen3-TTS).
Definer selvvalgte uttaler (ord = uttale):
-12
+12
Styrer ekspressivitet (0 = nøytral, 1 = svært ekspressiv)
Veiledningsvekt uten klassifikator (høyere = raskere oppfølging)
Beskriv stemmestilen på naturlig språk (Parler bruker dette i stedet for forhåndsinnstilte stemmer)
Dia- dialogformat: Bruk [S1] og [S2] tagger for å merke forskjellige høyttalere. Eksempel: [S1] Hei der! [S2] Hei, hvordan er du?
Dette er en premium- stemmemodell, tilgjengelig på en lønnet plan. Du kan likevel forhåndsvise stemmer gratis med spill- knappen ved siden av stemmevelgeren.
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.
Best for: High-quality TTS with minimal latency, streaming applications
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Største antall tegn
500
Kokoro stemmer
Adam
English
LedigMale
Alex
Spanish
LedigMale
Alex
Portuguese
LedigMale
Alpha
Hindi
LedigFemale
Alpha
Japanese
LedigFemale
Bella
English
LedigFemale
Dora
Spanish
LedigFemale
Dora
Portuguese
LedigFemale
Emma (British)
English
LedigFemale
George (British)
English
LedigMale
Gongitsune
Japanese
LedigFemale
Heart
English
LedigFemale
Isabella (British)
English
LedigFemale
Lewis (British)
English
LedigMale
Michael
English
LedigMale
Nicola
Italian
LedigMale
Nicole
English
LedigFemale
Omega
Hindi
LedigMale
Sara
Italian
LedigFemale
Sarah
English
LedigFemale
Siwis
French
LedigFemale
Sky
English
LedigFemale
Xiaobei
Chinese
LedigFemale
Xiaoni
Chinese
LedigFemale
Xiaoxiao
Chinese
LedigFemale
Yunjian
Chinese
LedigMale
Kokoro TTS — OSS
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.
