# Text-to-Speech on Seed-TTS Seed-ZH (test) Source: [Text-to-Speech on Seed-TTS Seed-ZH (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:08:34.149Z Evaluation of Text-to-Speech synthesis performance on the test split of the Seed-TTS Seed-ZH dataset, using Word Error Rate (WER) and Structural Similarity Index Measure (SSIM). 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 (test) | | Metric | WER | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 11 of 11 | | 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. - [SSIM](): Higher is better; unit: SCALAR. ## Recorded results | Method | WER | Result date | Report paper | | --- | --- | --- | --- | | DiTAR | 1.02 | Not recorded | 69857574c97a0b3e3b5d5b84 | | Seed-TTS\_DiT | 1.178 | Not recorded | 69857574c97a0b3e3b5d5b84 | | Ground Truth | 1.254 | Not recorded | 69857574c97a0b3e3b5d5b84 | | Vocos Resynthesized | 1.27 | Not recorded | 69857574c97a0b3e3b5d5b84 | | ARCHI-TTS | 1.42 | Not recorded | 69857574c97a0b3e3b5d5b84 | | VAE Resynthesized | 1.44 | Not recorded | 69857574c97a0b3e3b5d5b84 | | CosyVoice 2 | 1.45 | Not recorded | 69857574c97a0b3e3b5d5b84 | | FireRedTTS | 1.51 | Not recorded | 69857574c97a0b3e3b5d5b84 | | F5-TTS | 1.56 | Not recorded | 69857574c97a0b3e3b5d5b84 | | E2 TTS | 1.97 | Not recorded | 69857574c97a0b3e3b5d5b84 | | MaskGCT | 2.273 | Not recorded | 69857574c97a0b3e3b5d5b84 | ### DiTAR WER: 1.02. Result ID: 699a108d5698665ec49437e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed-TTS\_DiT WER: 1.178. Result ID: 699a108d5698665ec49437dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ground Truth WER: 1.254. Result ID: 699a108d5698665ec49437d7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Vocos Resynthesized WER: 1.27. Result ID: 699a108d5698665ec49437d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ARCHI-TTS WER: 1.42. Result ID: 699a108d5698665ec49437e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VAE Resynthesized WER: 1.44. Result ID: 699a108d5698665ec49437d8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CosyVoice 2 WER: 1.45. Result ID: 699a108d5698665ec49437da. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FireRedTTS WER: 1.51. Result ID: 699a108d5698665ec49437db. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### F5-TTS WER: 1.56. Result ID: 699a108d5698665ec49437df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### E2 TTS WER: 1.97. Result ID: 699a108d5698665ec49437de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MaskGCT WER: 2.273. Result ID: 699a108d5698665ec49437dc. [Reporting paper]() [Method origin paper]() 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.