# Text-to-Speech on CV3-Eval Monolingual zh

Source: [Text-to-Speech on CV3-Eval Monolingual zh](<https://www.sota2.com/research/sota/text-to-speech-on-cv3-eval-monolingual-zh>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-08T07:26:58.146Z

Evaluation of Text-to-Speech synthesis quality on the CV3-Eval Monolingual Chinese dataset, measured using Word Error Rate (WER).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Text-to-Speech |
| Dataset (including any stated split) | CV3-Eval Monolingual zh |
| Metric | WER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [WER](<https://www.sota2.com/research/sota/text-to-speech-on-cv3-eval-monolingual-zh.md?metric=WER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| Fish-Audio S2 | 2.65 | Not recorded | 6a264c6390966ade919be869 |
| dots.tts | 3.51 | Not recorded | 6a264c6390966ade919be869 |
| VoxCPM 2 | 3.65 | Not recorded | 6a264c6390966ade919be869 |
| dots.tts | 3.71 | Not recorded | 6a264c6390966ade919be869 |
| CosyVoice 3 | 3.91 | Not recorded | 6a264c6390966ade919be869 |
| dots.tts | 3.95 | Not recorded | 6a264c6390966ade919be869 |
| CosyVoice 2 | 4.08 | Not recorded | 6a264c6390966ade919be869 |

### Fish-Audio S2

WER: 2.65. Result ID: 6a266ebdfbc373592c22cf22.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b93.md>)

[Implementation](<https://github.com/fishaudio/fish-speech>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### dots.tts

WER: 3.51. Result ID: 6a266ebdfbc373592c22cf24.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Implementation](<https://github.com/rednote-hilab/dots.tts>)

Recorded evaluation configuration: {"Training Stage":"Pretrain"}. This record does not assert independent reproduction.

### VoxCPM 2

WER: 3.65. Result ID: 6a266ebdfbc373592c22cf23.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### dots.tts

WER: 3.71. Result ID: 6a266ebdfbc373592c22cf25.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Implementation](<https://github.com/rednote-hilab/dots.tts>)

Recorded evaluation configuration: {"Training Stage":"SOAR"}. This record does not assert independent reproduction.

### CosyVoice 3

WER: 3.91. Result ID: 6a266ebdfbc373592c22cf21.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78dd1e209131cea7ae5b.md>)

Recorded evaluation configuration: {"Number of Parameters":"1.5B"}. This record does not assert independent reproduction.

### dots.tts

WER: 3.95. Result ID: 6a266ebdfbc373592c22cf26.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Implementation](<https://github.com/rednote-hilab/dots.tts>)

Recorded evaluation configuration: {"Training Stage":"MF","NFE (Number of Function Evaluations)":"4"}. This record does not assert independent reproduction.

### CosyVoice 2

WER: 4.08. Result ID: 6a266ebdfbc373592c22cf20.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c6390966ade919be869.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76591e209131cea6c851.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.