Soratra mankany amin'ny feo Mpiasa AI Mozika Soraty Fandraisana an-tsoratra feo Famolavolana ny feo Marketplace More
Tatero kilema / fangatahana endri-javatra
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 marika · Misoratra anarana ho an'ny 5.000 isan-taranaka →
Misoratra anarana fetra 5000 marika

Ampidiro anatin'ny tag SSML ny lahabolana mba hahazoana fifehezana mazava tsara:

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

Tag fantatry ny modely voafaritra — tsindrio mba hametrahana iray ao anatin'ny lahatsoratrao izay misy azy:

Mamakiana lahabolana tsotra io modely io, ka tsy raharahaina ny tag anatin'ny andalana. Raha mila fihetseham-po mifototra amin'ny tag ianao, dia miova ho modely maneho fihetseham-po toy ny Orpheus na Bark.

Mamaritra ny fanononana safidy (teny = fanononana):

-12 +12
0.5x 2.0x
Malalaka miaraka amin'ny Piper, VITS, MeloTTS
Hiseho eto ny feo namoronanao. Misafidiana modely iray, soraty ny lahabolana, dia tsindrio ny Mamorona.
Namorona feo tsara
0:00
Handefa feo Hidina.srt Tapitra ao anatin'ny 24 ora ity rohy ity
Ny faritr'ora dia GMT+1. : Tranonkala ofisialy Lisansa ara-barotra manomboka amin'ny $5/volana
Tianao ve ny TTS.ai? Lazao amin'ny namanao!

Mombamomba 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.

Tsara indrindra ho an'ny: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice

Jereo izy rehetra Darwin TTS feo

Amin'ny fijery fohy

Mpamorona
FINAL-Bench
Lisansa
Apache 2.0
Taona
standard
Hafainganan'ny fanovana
medium
Fandraisana feo
Eny
Teny
English, Korean, Japanese, Chinese
Marika betsaka indrindra
2000

Darwin TTS feo

Default

English
Standard Neutral

Default (Chinese)

Chinese
Standard Neutral

Default (Japanese)

Japanese
Standard Neutral

Default (Korean)

Korean
Standard Neutral

Darwin TTS TTS - Fanontaniana matetika

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.
← Ny feo rehetra