Umbhalo usuka kumazwi Ama-AI Agents Umculo Ukukhuluma kuMbhalo Ukulungiswa kwezwi Uhlelo lwezwi Imakethe Okuningi
Umbiko wephutha / Umbuzo wezici
Darwin TTS

Darwin TTS TTS

A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.

0/500 amaphawu · Ubhalise nge-5,000 ngenkulumo →
Bhala for 5,000 characters limit

Ukufaka umbhalo wakho kumathegi we-SSML ukulawula okucacile:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Amathegi amamodeli akhethiwe aqonda - chofoza ukuwasusa kusihloko sakho lapho kwenzeka khona:

Le modeli ifunda umbhalo ojwayelekile, ngakho amathegi e-inline akhohlwa. Ukwenza umbono osekelwe kumathegi, shintsha kwimodeli ebonisa umbono njenge-Orpheus noma i-Bark.

Chaza ukuchaza okujwayelekile (igama = ukuchaza):

-12 +12
0.5x 2.0x
Imahhala ne-Piper, VITS, MeloTTS
Umsindo wakho okhiqizwe uzovela lapha. Khetha imodeli, ngenisa umbhalo, bese uchofoza Ukukhiqiza.
Umsindo wakhiwa ngokuphumelelayo
0:00
Layisha phezulu umsindo Layisha phezulu.srt Isixhumanisi siphele ngehora le-24
Isikhashana esimahhala: ukusetshenziswa komuntu siqu. Ilayisense yebhizinisi kusuka ku-$5/mo
Yenza lokhu kube umsindo wakho Uhlu lwezinhlamvu
Uthanda i-TTS.ai? Ncoma abangane bakho!

Ngo Darwin TTS

Darwin-TTS-1.7B-Cross by FINAL-Bench is a research variant of Qwen3-TTS-1.7B with an unusual construction: 84 of its talker-FFN tensors (about 8.6% of them) are blended at a 3% ratio with the matching tensors from Qwen3-1.7B-Base, all without any retraining. The result is a model that produces noticeably crisper cross-lingual voice cloning across Korean, English, Japanese, and Chinese — its four core languages. It operates in zero-shot voice-clone mode, needing only about three seconds of reference audio to capture a speaker. Darwin is best suited to transferring a single reference voice across those four languages, for example dubbing or multilingual narration with consistent speaker identity.

Okungcono kakhulu: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice

Khangela konke Darwin TTS izizwi

Ngombono ocacile

Umthuthukisi
FINAL-Bench
Ilayisense
Apache 2.0
I-Tiger
standard
Isivinini
medium
Ukuklona umsindo
Yebo
Izilimi
English, Korean, Japanese, Chinese
Amaphawu aphezulu
2000

Darwin TTS izizwi

Default

English
Iphutha Neutral

Default (Chinese)

Chinese
Iphutha Neutral

Default (Japanese)

Japanese
Iphutha Neutral

Default (Korean)

Korean
Iphutha Neutral

Darwin TTS Imibuzo ebuzwa kaningi

Darwin starts from Qwen3-TTS-1.7B but blends a small fraction of its talker-FFN weights with the matching weights from the Qwen3-1.7B base language model. This training-free blend sharpens cross-lingual voice cloning rather than changing the base voices.

English, Korean, Japanese, and Chinese. The FINAL-Bench release specifically markets its cross-lingual blend for those four, and the deployed model ships voices for them.

About three seconds. It works in zero-shot mode, so no fine-tuning or training is required — you provide a short reference clip and it generates new speech in that voice.
← Zonke izizwi