Bark Small TT TT TTT TTT T TT TT T T TTT TTT TTT
A distilled 150M version of Suno's Bark that trades some fidelity for roughly twice the speed and half the memory.
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) :
关于 Bark Small
Bark Small is Suno's distilled, lightweight take on Bark, shrinking the model to 150M parameters. It keeps Bark's signature ability to produce emotional speech, laughter, and multilingual output across the same 13+ languages, but generates noticeably faster (~8s versus ~15s) and fits in about 2GB of VRAM. The cost is some audio quality, so it works best as the go-to when full Bark is too slow for a creative task but you still want its expressive, sound-rich character. Like full Bark it caps at 200 characters per generation and does not support voice cloning.
最佳: Quick creative audio when full Bark is too slow
全部浏览 Bark Small 声音一眼看一眼,
- 开发者
- Suno
- 许可证
- MIT
- 级别
- standard
- 速度
- medium
- 语音克隆
- 否 无
- 语言
- English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
- 最大字符
- 200