whatmodel.sh / tts / Qwen3-TTS 12Hz 0.6B CustomVoice
Qwen3-TTS 12Hz 0.6B CustomVoice
↗ share
+ contribute
Qwen3-TTS 12Hz 0.6B CustomVoice is an open-weights text-to-speech model from Alibaba (Qwen), released January 2026. Licence: apache-2.0.
Catalogue identity notes
Comparison-only. Exact checkpoint Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice (HF sha 85e237c at 2026-10-08, created 2026-01-21, Apache-2.0), the preset-speaker variant; distinct from the catalogue's qwen3-tts-12hz-0-6b-base (voice-cloning base). carun/tts-bench engines/run_qwen.py loads exactly this repo with speaker 'Aiden'. Needed so the new carun-tts-bench56 benchmark reaches 3 models (run already has Kokoro-82M and Magpie 357M).
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 Qwen3-TTS 12Hz 0.6B CustomVoice, out of 148 with a score, then more from Alibaba (Qwen).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 96 |  Piper (en_US lessac medium) | 47±5 | local | ||
| 97 |  Vevo (Amphion) | 46±3 | local | ||
| 98 | Qwen3-TTS 12Hz 0.6B CustomVoice | 46±6 | comparison only | ||
| 99 |  Dia2 2B | 45±6 | local | ||
| 100 |  Amazon Polly Neural | 45±4 | api $16.00/M chars | ||
| more from Alibaba (Qwen) | |||||
| 25 | Qwen3-TTS 12Hz 1.7B Base | 65±1 | local | ||
| 44 | Qwen3-TTS 12Hz 0.6B Base | 62±2 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 85% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| carun tts-bench · 56-sentence English corpus · Whisper large-v3 WER | 4.1% ✎ | █····█·····█ beats 1/2 | 85% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/Qwen ↗
$ how the score was worked out · carun/tts-bench: intelligibil… 85%
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 |
|---|---|---|
 carun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10) | 1 | 85% |
| prior · pull toward the middle | 15% | |
| weighted average | = 45.7 |
$ 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