Darwin TTS TTS-värden
A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.
Radera din text i SSML-taggar för exakt kontroll:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Taggar den valda modellen förstår — klicka för att släppa en i din text där det händer:
Den här modellen läser vanlig text, så inline-taggar ignoreras. För taggbaserade känslor, byt till en uttrycksfull modell som Orpheus eller Bark.
Definiera egna uttal (ord = uttal):
Om jag inte kan 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.
Bäst för: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice
Bläddra alla Darwin TTS rösterMed en blick
- Utvecklare
- FINAL-Bench
- Licens
- Apache 2.0
- Nivå
- standard
- Varvtal
- medium
- Röstkloning
- Ja, det är jag.
- Språk
- English, Korean, Japanese, Chinese
- Max tecken
- 2000