文本到语音 AI 代理商 音乐 对文本的语音 语音克隆 语音设计 市场地点 更多
报告错误/功能要求
Darwin TTS

Darwin TTS TT TT TTT TTT T TT TT T T TTT TTT TTT

A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.

0/500 字符 · 每一代5,000人签名 →
签名 对 5,000 字符限制的 5 000 个字符

在 SSML 标记中折行文本以精确控制 :

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

标记选中模式的理解度 - 单击将一个输入到文本中, 发生时 :

这个模型读的是简单的文字, 所以内嵌标签会被忽略。 对于基于标签的情感, 请切换到像 Orpheus 或 Bark 这样的表达模式 。

定义自定义发音( Word = 发音) :

-12 +12
0.5x 2.0x
免费的管道、VITS、MelotTS
您生成的音频将在此显示。 选择一个模型, 输入文本, 并单击生成 。
音频生成成功
0:00
下载音频 下载.strt 24小时后链接过期
免费:个人使用。 5美元/美元商业许可证
使这个声音成为你自己的声音 30秒后打开声音
喜欢TTS.ai吗？告诉你的朋友吧！

关于 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.

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

全部浏览 Darwin TTS 声音

一眼看一眼,

开发者
FINAL-Bench
许可证
Apache 2.0
级别
standard
速度
medium
语音克隆
是
语言
English, Korean, Japanese, Chinese
最大字符
2000

Darwin TTS 声音

Default

English
标准 Neutral

Default (Chinese)

Chinese
标准 Neutral

Default (Japanese)

Japanese
标准 Neutral

Default (Korean)

Korean
标准 Neutral

Darwin TTS TTS - 常见问题

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.
← 所有声音