Tags y deall y model dewisiedig - cliciwch i daflu un i' ch testun lle mae' n digwydd:
Mae'r model yma yn darllen testun plaen, felly anwybyddir tagiau mewnlin. I ddelweddu teimlad yn seiliedig ar dagiau, newidiwch i ddelweddu mynegiant fel Orpheus neu Bark.
Cynghorion dosbarthu iaith naturiol. Yn cael eu cydnabod gan Qwen3-TTS heddiw; mae modelau mynegiant eraill yn dod yn fuan.
Nid yw'r model hwn yn cynnal cyfarwyddiadau arddull - newid i ddull sy'n gwneud hynny (e.e. Qwen3-TTS).
Diffinio ynganiad addasiedig (gair = ynganiad):
-12
+12
Rheoli mynegiant (0 = niwtral, 1 = yn fawr iawn)
Pwysau cyfarwyddyd di-gyfeiriadur (uwch = mwy o ganlyniadau)
Disgrifio'r arddull llais mewn iaith naturiol (Parler yn defnyddio hwn yn lle llais rhagosodedig)
Fformat Ymgom Dia: Defnyddiwch y tagiau [S1] a [S2] i nodi siaradwyr gwahanol. Enghraifft: [S1] Helo! [S2] Helo, sut ydych chi?
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.
Gorau ar gyfer: High-quality TTS with minimal latency, streaming applications
English, Japanese, Chinese, French, Italian, Portuguese, Spanish, Hindi
Uchafswm nodau
500
Kokoro Saesneg
Adam
English
RhyddMale
Alex
Spanish
RhyddMale
Alex
Portuguese
RhyddMale
Alpha
Hindi
RhyddFemale
Alpha
Japanese
RhyddFemale
Bella
English
RhyddFemale
Dora
Spanish
RhyddFemale
Dora
Portuguese
RhyddFemale
Emma (British)
English
RhyddFemale
George (British)
English
RhyddMale
Gongitsune
Japanese
RhyddFemale
Heart
English
RhyddFemale
Isabella (British)
English
RhyddFemale
Lewis (British)
English
RhyddMale
Michael
English
RhyddMale
Nicola
Italian
RhyddMale
Nicole
English
RhyddFemale
Omega
Hindi
RhyddMale
Sara
Italian
RhyddFemale
Sarah
English
RhyddFemale
Siwis
French
RhyddFemale
Sky
English
RhyddFemale
Xiaobei
Chinese
RhyddFemale
Xiaoni
Chinese
RhyddFemale
Xiaoxiao
Chinese
RhyddFemale
Yunjian
Chinese
RhyddMale
Kokoro TTS - Cwestiynau Cyffredin
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.
