whatmodel.sh / tts / Raon-OpenTTS-0.3B
Raon-OpenTTS-0.3B
↗ share
+ contribute
Raon-OpenTTS-0.3B is an open-weights text-to-speech model from KRAFTON, released April 2026. Its published size is 0.3B parameters. Licence: cc-by-nc-4.0.
Catalogue identity notes
KRAFTON/Raon-OpenTTS-0.3B, trained only on open speech data (arXiv:2605.20830).
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 Raon-OpenTTS-0.3B, out of 148 with a score, then more from KRAFTON.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 22 |  Chirp 3: HD | 65±4 | api $30.00/M chars | ||
| 23 |  Higgs Audio V3 TTS | 65±3 | api $15.00/M chars +local | ||
| 24 | Raon-OpenTTS-0.3B | 65±2 | comparison only | ||
| 25 |  Qwen3-TTS 12Hz 1.7B Base | 65±1 | local | ||
| 26 |  VoxCPM 0.5B | 64±1 | local | ||
| more from KRAFTON | |||||
| 10 | Raon-OpenTTS-1B | 68±2 | comparison only | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
voice cloning▁·▁▁▁▁▁▁██▃▃ #24 of 43 * · 20% of its score · 2 tests
Beats Gemini 3.1 Flash TTS Preview here, though they rank higher overall. Trails E2 TTS Base (F5-TTS reproduction), DMOSpeech 2, Qwen3-TTS 12Hz 0.6B Base 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 | 68.7% ✎ | ▄····▄·█▄█▄▄ beats 2/8 | 13% |
| Seed-TTS test-en · Whisper large-v3 WER lab | 1.9% ✎ | ▄···█▄▄·█▄·▄ beats 6/8 | 6.3% |
other tests7 not in a task · 79% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CV3-Eval EN (zero-shot English) · WER lab | 4.6% ✎ | ▄··▄··▄▄·█·▄ beats 4/6 | 19% |
| CV3-Eval hard-en · speaker similarity (ERes2Net SV) lab | 73.0% ✎ | ▄··█··▄·█··▄ beats 4/6 | 13% |
| CV3-Eval hard-en · DNSMOS (predicted quality) lab | 3.77 / 5 ✎ | ▄·····█·▄▄·█ beats 1/6 | 11% |
| Raon-OpenTTS-Eval · overall speaker similarity (WavLM) lab | 62.3% ✎ | ▄·█·█▄·····▄ beats 1/6 | 11% |
| Raon-OpenTTS-Eval · human speaker-similarity MOS (overall) lab | 3.60 / 5 ✎ | █··██······▄ beats 5/6 | 10% |
| CV3-Eval hard-en · WER lab | 7.3% ✎ | ▄·······█·██ beats 4/6 | 10% |
| Raon-OpenTTS-Eval · overall WER (4 acoustic conditions) lab | 2.9% ✎ | ▄··▄█····▄·█ beats 5/6 | 5.5% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/KRAFTON ↗
$ how the score was worked out · Raon-OpenTTS: Open Models and… 99%
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 |
|---|---|---|
 Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2) · lab-reported | 9 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 64.9 |
$ 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