HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

dots.tts-soar

dots-studio/dots.tts-soar

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
rednote-hilab/dots.tts-base
provider
dots-studio
license
apache-2.0
language
—
context
—
library
dots_tts
vRAM (GB)
—
size on disk
—
downloads
1,597
likes
89
created
—
last modified
2026-06-10T08:33:39+00:00 (2026)
huggingface
https://huggingface.co/dots-studio/dots.tts-soar
tags
dots_ttssafetensorstext-to-speechttsaudiospeech-synthesisvoice-cloningautoregressiveflow-matchingpost-trainedbase_model:dots-studio/dots.tts-basebase_model:finetune:dots-studio/dots.tts-baselicense:apache-2.0region:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
Speaker SIMspeech-tts76.6low| MiniMax | **2.8** | 76.6 |
WERspeech-asr2.8low| MiniMax | **2.8** | 76.6 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.