Testutik hizketara Agenteak Musika Audioa testura Ahots klonaketa Ahots-diseinua Merkatua Gehiago
Txostendu programa- errorea / Eskaera
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 karaktereak · 5.000 belaunaldiko. →
Izena eman 5.000 karaktereko muga

Itzulbiratu zure testua SSML etiketetan kontrol zehatzagoa lortzeko:

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

Hautatutako modeloak ulertzen dituen etiketak — egin klik testuan jartzeko:

Eredu honek testu arrunta irakurtzen du, beraz, lerro-barneko etiketei ez zaie jaramonik egiten. Etiketetan oinarritutako emozioetarako, aldatu Orpheus edo Bark bezalako adierazpen-modelo batera.

Definitu ahoskera pertsonalizatuak (hitza = ahoskera):

-12 +12
0.5x 2.0x
Librea Piper, VITS, MeloTTS-ekin
Zure sortutako audioa hemen agertuko da. Aukeratu modelo bat, idatzi testua eta egin klik Sortu botoian.
Audioa behar bezala sortu da
0:00
Deskargatu audioa Deskargatu.srt Esteka 24 ordutan iraungiko da
Librea: erabiltzaile pribatuentzat. Lizentzia komertziala $5/mo-tik
Maite TTS.ai? Esan zure lagunei!

Honi buruz 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.

Honako hauentzako onena: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice

Arakatu dena Darwin TTS ahotsak

Begirada batean

Garatzailea
FINAL-Bench
Lizentzia
Apache 2.0
Tier
standard
Abiadura
medium
Ahots klonaketa
Bai
Hizkuntzak
English, Korean, Japanese, Chinese
Gehienezko karaktereak
2000

Darwin TTS ahotsak

Default

English
Lehenetsia Neutral

Default (Chinese)

Chinese
Lehenetsia Neutral

Default (Japanese)

Japanese
Lehenetsia Neutral

Default (Korean)

Korean
Lehenetsia Neutral

Darwin TTS TTS — Galdera ohikoenak

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.
← Ahots guztiak