# Zero-shot Voice Cloning on Seed-TTS-Eval zh-hard (test) Source: [Zero-shot Voice Cloning on Seed-TTS-Eval zh-hard (test)]() Collection index: [llms.txt]() Data updated: 2026-06-08T07:26:58.094Z Evaluation of Zero-shot Voice Cloning performance on the challenging Chinese subset ('zh-hard') test split of the Seed-TTS-Eval dataset, measured using Word Error Rate (WER) and Similarity (SIM). 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 | Zero-shot Voice Cloning | | Dataset (including any stated split) | Seed-TTS-Eval zh-hard (test) | | Metric | WER | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 12 of 12 | | 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](): Lower is better; unit: PERCENT. - [Similarity Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | WER | Result date | Report paper | | --- | --- | --- | --- | | CosyVoice 3 | 5.83 | Not recorded | 6a264c6390966ade919be869 | | dots.tts (Pretrain) | 6.46 | Not recorded | 6a264c6390966ade919be869 | | dots.tts (SOAR) | 6.6 | Not recorded | 6a264c6390966ade919be869 | | dots.tts (MF, NFE=4) | 6.6 | Not recorded | 6a264c6390966ade919be869 | | Qwen3-TTS | 6.76 | Not recorded | 6a264c6390966ade919be869 | | IndexTTS 2 | 7.12 | Not recorded | 6a264c6390966ade919be869 | | dots.tts (MF, NFE=3) | 7.19 | Not recorded | 6a264c6390966ade919be869 | | Seed-TTS | 7.59 | Not recorded | 6a264c6390966ade919be869 | | dots.tts (MF, NFE=2) | 7.74 | Not recorded | 6a264c6390966ade919be869 | | VoxCPM 2 | 8.13 | Not recorded | 6a264c6390966ade919be869 | | F5-TTS | 8.67 | Not recorded | 6a264c6390966ade919be869 | | FireRedTTS 2 | 8.98 | Not recorded | 6a264c6390966ade919be869 | ### CosyVoice 3 WER: 5.83. Result ID: 6a266ebdfbc373592c22cef9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"1.5B"}. This record does not assert independent reproduction. ### dots.tts (Pretrain) WER: 6.46. Result ID: 6a266ebdfbc373592c22cf00. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B","Variant":"Pretrain"}. This record does not assert independent reproduction. ### dots.tts (SOAR) WER: 6.6. Result ID: 6a266ebdfbc373592c22cf01. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B","Variant":"SOAR"}. This record does not assert independent reproduction. ### dots.tts (MF, NFE=4) WER: 6.6. Result ID: 6a266ebdfbc373592c22cf02. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B","Distillation Method":"MeanFlow","NFE":"4"}. This record does not assert independent reproduction. ### Qwen3-TTS WER: 6.76. Result ID: 6a266ebdfbc373592c22cefd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"1.7B"}. This record does not assert independent reproduction. ### IndexTTS 2 WER: 7.12. Result ID: 6a266ebdfbc373592c22cefc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"1.5B"}. This record does not assert independent reproduction. ### dots.tts (MF, NFE=3) WER: 7.19. Result ID: 6a266ebdfbc373592c22cf03. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B","Distillation Method":"MeanFlow","NFE":"3"}. This record does not assert independent reproduction. ### Seed-TTS WER: 7.59. Result ID: 6a266ebdfbc373592c22cefe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### dots.tts (MF, NFE=2) WER: 7.74. Result ID: 6a266ebdfbc373592c22cf04. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"2B","Distillation Method":"MeanFlow","NFE":"2"}. This record does not assert independent reproduction. ### VoxCPM 2 WER: 8.13. Result ID: 6a266ebdfbc373592c22ceff. [Reporting paper]() Recorded evaluation configuration: {"Params":"2B"}. This record does not assert independent reproduction. ### F5-TTS WER: 8.67. Result ID: 6a266ebdfbc373592c22cefa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"0.3B"}. This record does not assert independent reproduction. ### FireRedTTS 2 WER: 8.98. Result ID: 6a266ebdfbc373592c22cefb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"1.5B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.