# Text-to-Speech on Seed-TTS Seed-ZH (Evaluation)

Source: [Text-to-Speech on Seed-TTS Seed-ZH (Evaluation)](<https://www.sota2.com/research/sota/text-to-speech-on-seed-tts-seed-zh-evaluation>)

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

Data updated: 2026-02-26T05:38:16.634Z

Evaluation of Text-to-Speech synthesis performance on the Seed-TTS Seed-ZH (Evaluation) set, utilizing Character Error Rate (CER) and Similarity (SIM) metrics.

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) | Seed-TTS Seed-ZH (Evaluation) |
| Metric | CER |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 16 of 16 |
| 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

- [CER](<https://www.sota2.com/research/sota/text-to-speech-on-seed-tts-seed-zh-evaluation.md?metric=CER>): Lower is better; unit: SCALAR.

- [SIM Score](<https://www.sota2.com/research/sota/text-to-speech-on-seed-tts-seed-zh-evaluation.md?metric=SIM%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CER | Result date | Report paper |
| --- | --- | --- | --- |
| GLM-TTS | 0.89 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| VoxCPM | 0.93 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| IndexTTS2 | 1.03 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| CosyVoice3-1.5B | 1.12 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| FireRedTTS2 | 1.14 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| VibeVoice | 1.16 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| OpenAudio-s1-mini | 1.18 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| SparkTTS | 1.2 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| CAT-TTS | 1.23 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| CosyVoice2 | 1.38 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| HiggsAudio-v2 | 1.5 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| FireRedTTS | 1.51 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| F5-TTS | 1.53 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| Llasa | 1.59 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| Qwen2.5-Omni | 1.7 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |
| MaskGCT | 2.27 | Not recorded | 698d5ed4c97a0b3e3b5e3fe5 |

### GLM-TTS

CER: 0.89. Result ID: 6999fb185698665ec47c9f55.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694238fd456146936285052a.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### VoxCPM

CER: 0.93. Result ID: 6999fb185698665ec47c9f58.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bb81e209131cea8a230.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"NAR / Continuous AR"}. This record does not assert independent reproduction.

### IndexTTS2

CER: 1.03. Result ID: 6999fb185698665ec47c9f54.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b1a1e209131cea86926.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### CosyVoice3-1.5B

CER: 1.12. Result ID: 6999fb185698665ec47c9f53.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

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

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### FireRedTTS2

CER: 1.14. Result ID: 6999fb185698665ec47c9f5d.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b251e209131cea86d8b.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### VibeVoice

CER: 1.16. Result ID: 6999fb185698665ec47c9f57.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7adc1e209131cea858bb.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"NAR / Continuous AR"}. This record does not assert independent reproduction.

### OpenAudio-s1-mini

CER: 1.18. Result ID: 6999fb185698665ec47c9f5b.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### SparkTTS

CER: 1.2. Result ID: 6999fb185698665ec47c9f5a.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77381e209131cea71c24.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### CAT-TTS

CER: 1.23. Result ID: 6999fb185698665ec47c9f5e.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Implementation](<https://github.com/OpenMOSS/MOSS-Audio-Tokenizer>)

Recorded evaluation configuration: {"Bitrate Control":true,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### CosyVoice2

CER: 1.38. Result ID: 6999fb185698665ec47c9f51.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74031e209131cea5f3e0.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### HiggsAudio-v2

CER: 1.5. Result ID: 6999fb185698665ec47c9f5c.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### FireRedTTS

CER: 1.51. Result ID: 6999fb185698665ec47c9f50.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b251e209131cea86d8b.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### F5-TTS

CER: 1.53. Result ID: 6999fb185698665ec47c9f56.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a71e209131cea79a4f.md>)

[Implementation](<https://github.com/SWivid/F5-TTS>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"NAR / Continuous AR"}. This record does not assert independent reproduction.

### Llasa

CER: 1.59. Result ID: 6999fb185698665ec47c9f59.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77211e209131cea7143b.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Discrete AR"}. This record does not assert independent reproduction.

### Qwen2.5-Omni

CER: 1.7. Result ID: 6999fb185698665ec47c9f52.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

### MaskGCT

CER: 2.27. Result ID: 6999fb185698665ec47c9f4f.

[Reporting paper](<https://www.sota2.com/research/paper/698d5ed4c97a0b3e3b5e3fe5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75531e209131cea672d9.md>)

Recorded evaluation configuration: {"Bitrate Control":false,"Architecture":"Cascade (AR+NAR / NAR+NAR)"}. This record does not assert independent reproduction.

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