Darwin TTS टीटीएस
A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.
अचूक नियंत्रण करीता SSML टॅग अंतर्गत पाठ्य वेल्ड करा:
<speak><prosody rate="slow">Slow speech</prosody></speak>
निवडलेले नमूना समजून घेणारे टॅग - पाठ्य अंतर्गत एक टाका जेथे ते घडते:
हे मॉडेल सादा पाठ्य वाचते, त्यामुळे इनलाईन टॅग दुर्लक्ष केले जातात. टॅग आधारीत भावना करीता, Orpheus किंवा Bark सारखे अभिव्यक्ती मॉडेल करीता बदलवा.
इच्छिक उच्चारण निश्चित करा (शब्द = उच्चारण):
विषयी 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.
सर्वोत्तम: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice
सर्व ब्राऊज करा Darwin TTS आवाजएक नजर
- डेव्हलपर
- FINAL-Bench
- परवाना
- Apache 2.0
- टर
- standard
- वेग
- medium
- आवाज क्लोन
- होय
- भाषाName
- English, Korean, Japanese, Chinese
- कमाल अक्षरे
- 2000