whatmodel.sh / tts / Qwen-Audio-3.0-TTS-Plus
Qwen-Audio-3.0-TTS-Plus
↗ share
+ contribute
Qwen-Audio-3.0-TTS-Plus is a closed-weights text-to-speech model from Alibaba, released September 2026. Licence: proprietary.
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 Qwen-Audio-3.0-TTS-Plus, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 5 |  OpenAudio S1 | 71±8 | api $15.00/M chars |
| 6 |  Gemini 2.5 Pro Preview TTS | 69±3 | comparison only |
| 7 | Qwen-Audio-3.0-TTS-Plus | 69±2 | api $20.00/M chars |
| 8 | Gemini 3.1 Flash TTS Preview | 69±2 | api $50.00/M chars |
| 9 |  dots.tts MF 2B (MeanFlow, NFE 4) | 68±3 | local |
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
voice cloning▁·▁▁▁▁▁▁▇█▃▃ #1 of 37 * · 20% of its score · 4 tests
Beats OpenAudio S1 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Seed-TTS test-zh · speaker similarity (ERes2Net SV) lab | 84.7% ✎ | █·····██···█ beats 3/3 | 10% |
| Seed-TTS test-en · speaker similarity (ERes2Net SV) lab | 81.5% ✎ | █····█··█··█ beats 3/3 | 10% |
| Seed-TTS test-en · Whisper large-v3 WER lab | 1.5% ✎ | ▁···▂▂▂▂█▆▄▂ beats 27/35 | — |
| Seed-TTS test-zh · Paraformer CER lab | 0.8% ✎ | ▁·▂▁▁▁▂▃▅█·▂ beats 28/30 | — |
other tests6 not in a task · 78% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CV3-Eval hard-en · WER lab | 6.7% ✎ | █····█·█████ beats 4/6 | 20% |
| CV3-Eval hard-en · DNSMOS (predicted quality) lab | 4.04 / 5 ✎ | █·▄·▄▄·▄···▄ beats 6/6 | 14% |
| CV3-Eval hard-zh · CER lab | 7.4% ✎ | ▄▄▄···▄··▄·█ beats 5/6 | 14% |
| CV3-Eval multilingual voice clone · 9-language mean error lab | 4.7% ✎ | ▄···▄··▄··██ beats 6/6 | 14% |
| CV3-Eval protocol, 7 added languages · mean WER (Qwen-Audio 3.0 extension) lab | 3.1% ✎ | █··█······██ beats 2/3 | 10% |
| CV3-Eval hard-en · speaker similarity (ERes2Net SV) lab | 76.6% ✎ | ▄·····▄▄·▄▄█ beats 6/6 | 6.6% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · $20.00/M chars · www.alibabacloud.com ↗ · price sourceUSD per 1M characters: Model Studio lists qwen-audio-3.0-tts-plus at $0.2 per 10,000 input characters, International (Singapore) deployment; output not billed (x100). Each Chinese character counts as 2 characters. Product: Alibaba Cloud Model Studio speech synthesis. API model: qwen-audio-3.0-tts-plus. Settings: International deployment. Price basis: published list rate. Exclusions: free quota; Mainland China deployment lists $0.19253 per 10,000. Currency: USD. Alibaba Cloud official pricing page, observed 2026-09-25.
$ how the score was worked out · Qwen-Audio-3.0-TTS technical… 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 |
|---|---|---|
 Qwen-Audio-3.0-TTS technical report · lab-reported | 8 | 98% |
| prior · pull toward the middle | 2% | |
| weighted average | = 68.9 |
not counted (2)
| Qwen-Audio-3.0-TTS technical report | Seed-TTS test-zh · Paraformer CER [correct] | 0.8% | fewer than three models have this test yet, or this source ran it for this model alone |
| Qwen-Audio-3.0-TTS technical report | Seed-TTS test-en · Whisper large-v3 WER [correct] | 1.5% | fewer than three models have this test yet, or this source ran it for this model alone |
$ 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