Darwin TTS

Darwin TTS ټي ټي اېس

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

ننوتل د 5,000 لوښه حد

د دقیق کنټرول لپاره په SSML نښانونو خپل متن واچوئ:

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

توري د ټاکل شوي ماډل پوهیږي - کلیک وکړئ چې ستاسو په متن کې یو راښکته کړئ چیرې چې دا پیښیږي:

دا ماډل لوستل ساده متن، نو inline نښانونه په پام کې نه نيول کيږي. د نښان پر بنسټ احساس، د يو څرګند ماډل لکه Orpheus يا Bark بدل.

دوديزه لوستنه پېژندل (ويې = لوستنه):

-12 +12
0.5x 2.0x
د پيپر، VITS، MeloTTS سره وړيا
ستاسو توليد شوي غږيز به دلته ښکاره شي. يو ماډل وټاکئ، ليکنه وليکﺉ، او توليد کېکاږﺉ.
غږ په برياليتوب سره جوړ شو
0:00
غږيز رالېښنې .srt ډاونلوډ تړنه په 24h کې پای ته رسیږي
وړیا طبقه: شخصي کارولو. د $ 5 / mo څخه سوداګریز جواز
TTS.ai مینه؟ خپل ملګرو ته ووایاست!

په اړه 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.

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

ټول لټول Darwin TTS غږونه

په يوه کتنه کې

جوړوونکی
FINAL-Bench
منښتليک
Apache 2.0
:د پاڼې نوم
standard
چټکتيا
medium
غږ کلونول
هو
ژبې
English, Korean, Japanese, Chinese
ټولوجګه لوښه
2000

Darwin TTS غږونه

Default

English
تلواله Neutral

Default (Chinese)

Chinese
تلواله Neutral

Default (Japanese)

Japanese
تلواله Neutral

Default (Korean)

Korean
تلواله Neutral

Darwin TTS د پوښتنو ځوابول

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.
← ټول غږونه