whatmodel.sh / tts / dots.tts Base (Pretrain) 2B
dots.tts Base (Pretrain) 2B
↗ share
+ contribute
dots.tts Base (Pretrain) 2B is an open-weights text-to-speech model from dots.tts, released June 2026. Its published size is 2B parameters. Licence: apache-2.0.
Catalogue identity notes
Comparison-only, proposed so the dots.tts report's Seed-TTS-Eval runs count. The report's 'dots.tts (Pretrain)' row is 'produced with the pretrained checkpoint from Section 3.2.2' (arXiv:2606.07080v2 §3.3.1); the released repo dots-studio/dots.tts-base (sha b5aac65a395e04a60a8dacd4e2f4aadc5ad3dbe1, created 2026-06-03, apache-2.0) describes itself as 'the end-to-end pretrained checkpoint trained on ~1.5M hours of speech' / 'Pretrain (~1.5M h)' and prints the identical Seed-TTS-Eval row (test-en 1.34 / 76.8, test-zh 0.96 / 80.5). Not dots.tts-soar (self-corrective post-trained) or dots.tts-mf (MeanFlow-distilled). params_b is the maker's rounded '2B' system figure (Table 2 Params column); HF safetensors metadata total 2,198,091,778.
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of dots.tts Base (Pretrain) 2B, out of 148 with a score, then more from dots.tts.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 12 |  FireRedTTS3 (base) | 67±3 | local | ||
| 13 |  Simba 3.2 | 67±3 | api $6.00/M chars | ||
| 14 | dots.tts Base (Pretrain) 2B | 67±2 | comparison only | ||
| 15 |  MiniMax Speech 2.8 Turbo | 66±3 | api $60.00/M chars | ||
| 16 |  LongCat-AudioDiT-3.5B | 66±2 | local | ||
| more from dots.tts | |||||
| 9 | dots.tts MF 2B (MeanFlow, NFE 4) | 68±3 | local | ||
| 20 | dots.tts SOAR 2B | 65±2 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
voice cloning▁·▁▁▁▁▁▁██▃▃ #5 of 43 · 39% of its score · 4 tests
Beats Gemini 3.1 Flash TTS Preview, dots.tts MF 2B (MeanFlow, NFE 4), FireRedTTS3 (base) here, though they rank higher overall. Trails dots.tts SOAR 2B, LongCat-AudioDiT-3.5B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Seed-TTS test-en · speaker similarity (WavLM-large SV) lab | 76.8% ✎ | ▁·▂▂▂█▆▃▅··▂ beats 24/30 | 15% |
| Seed-TTS test-zh · speaker similarity (WavLM-large SV) lab | 80.5% ✎ | ▁·▂··▂·█▄·▃▄ beats 21/25 | 13% |
| Seed-TTS test-en · Whisper large-v3 WER lab | 1.3% ✎ | ▁···▂▂▂▂█▆▄▂ beats 31/35 | 6.1% |
| Seed-TTS test-zh · Paraformer CER lab | 1.0% ✎ | ▁·▂▁▁▁▂▃▅█·▂ beats 20/30 | 4.5% |
other tests3 not in a task · 59% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CV3-Eval hard-en · WER lab | 6.0% ✎ | ▂······▅▅██▃ beats 15/18 | 24% |
| CV3-Eval EN (zero-shot English) · WER lab | 5.2% ✎ | ▁·······▁▃█▇ beats 6/14 | 20% |
| CV3-Eval hard-zh · CER lab | 9.7% ✎ | ▃▅·▃▃▅▅▃▅▃·█ beats 4/15 | 15% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/dots-studio ↗
$ how the score was worked out · dots.tts Technical Report 98%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 dots.tts Technical Report · lab-reported | 7 | 98% |
| prior · pull toward the middle | 2% | |
| weighted average | = 66.6 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json