Etiquetas que o modelo escollido entende - prema para deixar unha no texto onde ocorre:
Este modelo le texto simple, polo que se ignoran as etiquetas inline. Para emocións baseadas en etiquetas, cambie a un modelo expresivo como Orpheus ou Bark.
Indicacións de entrega de linguaxe natural. Honrado por Qwen3- TTS hoxe; outros modelos expresivos en breve.
Este modelo non admite instrucións de estilo; cambie a un modelo que o faga (por ex. Qwen3- TTS).
Controla a expresividade (0 = neutro, 1 = moi expresivo)
Peso de guía libre de clasificadores (maior = máis seguimento)
Describa o estilo de voz en linguaxe natural (Parler usa isto no canto das voces predefinidas)
Formato do diálogo Dia: Empregue as etiquetas < code> [S1] e < code> [S2] para marcar diferentes oradores. Exemplo: < code> [S1] Ola! [S2] Ola, como está?
Este é un modelo de voz premium, dispoñíbel en calquera plan de pago. Pode previsualizar as súas voces gratuitamente co botón de reprodución xunto ao selector de voz.
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.
Mellor para: High-quality TTS with minimal latency, streaming applications
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Caracteres máximos
500
Kokoro voces
Adam
English
LibreMale
Alex
Spanish
LibreMale
Alex
Portuguese
LibreMale
Alpha
Hindi
LibreFemale
Alpha
Japanese
LibreFemale
Bella
English
LibreFemale
Dora
Spanish
LibreFemale
Dora
Portuguese
LibreFemale
Emma (British)
English
LibreFemale
George (British)
English
LibreMale
Gongitsune
Japanese
LibreFemale
Heart
English
LibreFemale
Isabella (British)
English
LibreFemale
Lewis (British)
English
LibreMale
Michael
English
LibreMale
Nicola
Italian
LibreMale
Nicole
English
LibreFemale
Omega
Hindi
LibreMale
Sara
Italian
LibreFemale
Sarah
English
LibreFemale
Siwis
French
LibreFemale
Sky
English
LibreFemale
Xiaobei
Chinese
LibreFemale
Xiaoni
Chinese
LibreFemale
Xiaoxiao
Chinese
LibreFemale
Yunjian
Chinese
LibreMale
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.
Introduza o seu correo electrónico para seguir xerando fala de balde, ou subscríbase para obter 15. 000 caracteres extra.
Non se precisa contrasinal — enviarémoslle unha ligazón para configurar un máis tarde.
Acadouse o límite de niveis libres
Esgotou os seus 5. 000 caracteres diarios gratuítos. Cree unha conta gratuíta para obter 15. 000 caracteres extra máis 10. 000 caracteres gratuítos cada mes.
