Darwin TTS TTS
A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.
Envolvu vian tekston en SSML- etikedojn por preciza kontrolo:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Etikedoj kiujn la elektita modelo komprenas - klaku por meti unu en vian tekston kie ĝi okazas:
This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.
Difini proprajn elparolojn (vorto = elparolo):
Pri 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.
Plej bona por: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice
Foliumi ĉiujn Darwin TTS voĉojUnu rigardo
- Programisto
- FINAL-Bench
- Licenco
- Apache 2.0
- Tamuz
- standard
- Rapideco
- medium
- Voĉo- klonado
- Jes
- Lingvoj
- English, Korean, Japanese, Chinese
- Maksimuma nombro da signoj
- 2000