Tag yang dipilih mengerti klik °C untuk memasukkan satu ke dalam teks Anda di mana hal itu terjadi:
Model ini membaca teks biasa, sehingga tag inline diabaikan. Untuk tag berbasis emosi, beralih ke model ekspresif seperti Orpheus atau Bark.
isyarat pengiriman bahasa alami. yang dihormati oleh Qwen3-TTS hari ini; model ekspresif lain akan segera datang.
Model ini tidak mendukung instruksi gaya å beralih ke model yang melakukan (misalnya Qwen3-TTS).
Definisikan pengucapan ubahan (kata = pelafalan):
-12
+12
Kontrol ekspresif (0 = netral, 1 = sangat ekspresif)
Berat panduan kelas-bebas (lebih tinggi = lebih prompt-following)
Gambarkan gaya suara dalam bahasa alami (Parler menggunakan ini bukan suara preset)
Format Dia Dialog: Gunakan [S1] dan [S2] tag untuk menandai speaker yang berbeda. Contoh: [S1] Hello there! [S2] Hi, bagaimana kabarmu?
Ini adalah model suara premium, tersedia pada setiap rencana yang dibayar. Anda masih dapat mempratinjau suaranya dengan tombol pemutaran di sebelah pemilih suara.
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.
Terbaik untuk: High-quality TTS with minimal latency, streaming applications
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Karakter maksimal
500
Kokoro suara
Adam
English
BebasMale
Alex
Spanish
BebasMale
Alex
Portuguese
BebasMale
Alpha
Hindi
BebasFemale
Alpha
Japanese
BebasFemale
Bella
English
BebasFemale
Dora
Spanish
BebasFemale
Dora
Portuguese
BebasFemale
Emma (British)
English
BebasFemale
George (British)
English
BebasMale
Gongitsune
Japanese
BebasFemale
Heart
English
BebasFemale
Isabella (British)
English
BebasFemale
Lewis (British)
English
BebasMale
Michael
English
BebasMale
Nicola
Italian
BebasMale
Nicole
English
BebasFemale
Omega
Hindi
BebasMale
Sara
Italian
BebasFemale
Sarah
English
BebasFemale
Siwis
French
BebasFemale
Sky
English
BebasFemale
Xiaobei
Chinese
BebasFemale
Xiaoni
Chinese
BebasFemale
Xiaoxiao
Chinese
BebasFemale
Yunjian
Chinese
BebasMale
Kokoro TTS °F 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.
