Subjective Speech Quality Evaluation on X-Voice (test)
4.82IMOSGT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GTLanguage=Croatian2026.05 | 4.82 | 4.36 | |
| GTLanguage=Danish2026.05 | 4.82 | 4.7 | |
| Qwen3-TTSLanguage=English2026.05 | 4.8 | 4.6 | |
| Fish Audio S2Language=English2026.05 | 4.8 | 4.37 | |
| GTLanguage=Lithuanian2026.05 | 4.78 | 4.68 | |
| GTLanguage=Romanian2026.05 | 4.74 | 4.2 | |
| Qwen3-TTSLanguage=Chinese2026.05 | 4.69 | 4.15 | |
| GTLanguage=Japanese2026.05 | 4.68 | 4.34 | |
| GTLanguage=Italian2026.05 | 4.68 | 4.36 | |
| Qwen3-TTSLanguage=Italian2026.05 | 4.64 | 4.62 | |
| X-Voices2Language=Romanian2026.05 | 4.64 | 4.02 | |
| X-Voices1Language=English2026.05 | 4.63 | 4.4 | |
| GTLanguage=Greek2026.05 | 4.62 | 3.78 | |
| X-Voices1Language=Indonesian2026.05 | 4.6 | 3.98 | |
| X-Voices2Language=Dutch2026.05 | 4.6 | 3.15 | |
| Qwen3-TTSLanguage=Korean2026.05 | 4.58 | 4.4 | |
| GTLanguage=Latvian2026.05 | 4.56 | 4.62 | |
| X-Voices1Language=Romanian2026.05 | 4.56 | 3.92 | |
| MOSS-TTSLanguage=English2026.05 | 4.55 | 4.23 | |
| GTLanguage=Bulgarian2026.05 | 4.55 | 4.45 | |
| LEMAS-TTSLanguage=Indonesian2026.05 | 4.52 | 3.92 | |
| GTLanguage=Estonian2026.05 | 4.52 | 4.54 | |
| X-Voices2Language=English2026.05 | 4.48 | 4.32 | |
| Qwen3-TTSLanguage=Japanese2026.05 | 4.46 | 4.54 | |
| X-Voices1Language=Vietnamese2026.05 | 4.46 | 3.78 | |
| GTLanguage=Russian2026.05 | 4.46 | 3.76 | |
| GTLanguage=Swedish2026.05 | 4.45 | 3.55 | |
| GTLanguage=Thai2026.05 | 4.44 | 4.02 | |
| X-Voices1Language=Dutch2026.05 | 4.43 | 3.4 | |
| Qwen3-TTSLanguage=French2026.05 | 4.42 | 4.16 | |
| Fish Audio S2Language=Chinese2026.05 | 4.4 | 3.83 | |
| GTLanguage=Indonesian2026.05 | 4.4 | 4.04 | |
| Qwen3-TTSLanguage=Russian2026.05 | 4.38 | 4.26 | |
| GTLanguage=Maltese2026.05 | 4.38 | 4.35 | |
| Fish Audio S2Language=Korean2026.05 | 4.36 | 4.08 | |
| X-Voices2Language=Vietnamese2026.05 | 4.36 | 3.84 | |
| GTLanguage=English2026.05 | 4.35 | 4.23 | |
| X-Voices1Language=Chinese2026.05 | 4.33 | 3.97 | |
| X-Voices2Language=Chinese2026.05 | 4.33 | 4.02 | |
| Qwen3-TTSLanguage=Spanish2026.05 | 4.32 | 4.28 | |
| GTLanguage=Korean2026.05 | 4.3 | 4 | |
| X-Voices1Language=Polish2026.05 | 4.28 | 3.72 | |
| LEMAS-TTSLanguage=English2026.05 | 4.27 | 3.5 | |
| X-Voices1Language=Italian2026.05 | 4.26 | 4.04 | |
| GTLanguage=Vietnamese2026.05 | 4.24 | 4.22 | |
| GTLanguage=Polish2026.05 | 4.22 | 3.72 | |
| X-Voices1Language=French2026.05 | 4.2 | 3.84 | |
| X-Voices1Language=Slovak2026.05 | 4.2 | 3.84 | |
| MOSS-TTSLanguage=French2026.05 | 4.18 | 3.9 | |
| Fish Audio S2Language=Italian2026.05 | 4.18 | 4.08 | |
| X-Voices2Language=Polish2026.05 | 4.18 | 3.58 | |
| GTLanguage=Slovenian2026.05 | 4.18 | 4.48 | |
| Fish Audio S2Language=Japanese2026.05 | 4.16 | 4.16 | |
| Qwen3-TTSLanguage=German2026.05 | 4.16 | 3.9 | |
| Fish Audio S2Language=Russian2026.05 | 4.16 | 3.76 | |
| Fish Audio S2Language=Spanish2026.05 | 4.15 | 3.75 | |
| GTLanguage=Dutch2026.05 | 4.13 | 4.03 | |
| LEMAS-TTSLanguage=Vietnamese2026.05 | 4.12 | 3.9 | |
| X-Voices1Language=Spanish2026.05 | 4.12 | 3.83 | |
| X-Voices1Language=Czech2026.05 | 4.12 | 4.24 | |
| X-Voices2Language=Indonesian2026.05 | 4.1 | 4.04 | |
| Fish Audio S2Language=French2026.05 | 4.1 | 4 | |
| X-Voices2Language=Maltese2026.05 | 4.08 | 3.7 | |
| GTLanguage=French2026.05 | 4.06 | 3.88 | |
| GTLanguage=Czech2026.05 | 4.06 | 3.66 | |
| X-Voices2Language=Estonian2026.05 | 4.04 | 3.9 | |
| Fish Audio S2Language=Dutch2026.05 | 4.03 | 3.68 | |
| X-Voices1Language=Maltese2026.05 | 4.03 | 3.88 | |
| LEMAS-TTSLanguage=Italian2026.05 | 4.02 | 3.84 | |
| X-Voices2Language=Italian2026.05 | 4.02 | 3.74 | |
| X-Voices2Language=Croatian2026.05 | 4.02 | 3.54 | |
| X-Voices1Language=Hungarian2026.05 | 4.02 | 3.4 | |
| X-Voices1Language=Lithuanian2026.05 | 4.02 | 3.48 | |
| GTLanguage=Spanish2026.05 | 4 | 3.45 | |
| X-Voices2Language=Spanish2026.05 | 4 | 3.98 | |
| X-Voices2Language=Slovak2026.05 | 4 | 3.74 | |
| X-Voices1Language=Russian2026.05 | 3.98 | 3.68 | |
| X-Voices1Language=Estonian2026.05 | 3.98 | 4.06 | |
| X-Voices1Language=Greek2026.05 | 3.98 | 3.86 | |
| X-Voices2Language=Greek2026.05 | 3.98 | 4.04 | |
| X-Voices2Language=Hungarian2026.05 | 3.98 | 3.4 | |
| MOSS-TTSLanguage=Chinese2026.05 | 3.97 | 3.87 | |
| X-Voices1Language=Thai2026.05 | 3.96 | 4.18 | |
| GTLanguage=German2026.05 | 3.96 | 3.44 | |
| X-Voices2Language=Czech2026.05 | 3.96 | 3.92 | |
| LEMAS-TTSLanguage=French2026.05 | 3.94 | 3.82 | |
| X-Voices2Language=French2026.05 | 3.94 | 3.84 | |
| MOSS-TTSLanguage=Spanish2026.05 | 3.92 | 3.83 | |
| GTLanguage=Chinese2026.05 | 3.91 | 3.53 | |
| X-Voices2Language=Danish2026.05 | 3.86 | 3.5 | |
| X-Voices1Language=Korean2026.05 | 3.84 | 3.4 | |
| MOSS-TTSLanguage=Korean2026.05 | 3.82 | 3.36 | |
| MOSS-TTSLanguage=Russian2026.05 | 3.82 | 3.44 | |
| X-Voices2Language=Latvian2026.05 | 3.82 | 3.8 | |
| X-Voices2Language=Lithuanian2026.05 | 3.76 | 3.24 | |
| MOSS-TTSLanguage=Swedish2026.05 | 3.73 | 2.85 | |
| LEMAS-TTSLanguage=Portuguese2026.05 | 3.7 | 3.2 | |
| X-Voices2Language=Russian2026.05 | 3.7 | 3.14 | |
| X-Voices1Language=Croatian2026.05 | 3.7 | 3.62 | |
| X-Voices1Language=Danish2026.05 | 3.7 | 3.94 |