Darwin TTS TTS
A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.
Envolva o seu texto em tags SSML para controle preciso:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Etiquetas o modelo selecionado entende — clique para soltar um para o seu texto onde acontece:
Este modelo lê texto simples, por isso as etiquetas inline são ignoradas. Para emoção baseada em tags, mude para um modelo expressivo como Orpheus ou Bark.
Definir pronúncias personalizadas (palavra = pronúncia):
Sobre 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.
Melhor para: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice
Procurar todos Darwin TTS vozesDe uma olhada
- Desenvolvedor
- FINAL-Bench
- Licença
- Apache 2.0
- Tier
- standard
- Velocidade
- medium
- Clonagem de voz
- Sim
- Línguas
- English, Korean, Japanese, Chinese
- Número máximo de caracteres
- 2000