Benchmark
EmergentTTS-Eval Foreign Words WER
Scores are percentages. Lower is better.
- Models measured
- 9
- Scores recorded
- 14
- Sources
- 1
- IQ weight
- 0.42
Score distribution
- 15.6%
- Mean
- 14.5%
- Median
- 3.9%
- Std dev
- 12.1%
- 10th percentile
- 22.3%
- 90th percentile
- 11.8%
- Min
This benchmark has a weight of 0.42 for speech models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash TTSvoice: Zephyr, strong-prompt· EmergentTTS-Eval data | 11.8% |
| 2 | GPT-4o mini TTSvoice: Alloy, strong-prompt· EmergentTTS-Eval data | 12.1% |
| 3 | GPT-4o mini Audio Previewvoice: Alloy, strong-prompt· EmergentTTS-Eval data | 12.7% |
| 4 | Gemini 2.5 Flash TTSvoice: Zephyr· EmergentTTS-Eval data | 13% |
| 5 | GPT-4o Audio Previewvoice: Ballad, strong-prompt· EmergentTTS-Eval data | 13.3% |
| 6 | GPT-4o mini TTSvoice: Alloy, baseline· EmergentTTS-Eval data | 13.4% |
| 7 | GPT-4o Audio Previewvoice: Alloy, strong-prompt· EmergentTTS-Eval data | 13.8% |
| 8 | GPT-4o mini Audio Previewvoice: Alloy· EmergentTTS-Eval data | 14.5% |
| 9 | Speech 02 HDvoice: English_expressive_narrator· EmergentTTS-Eval data | 14.6% |
| 10 | GPT-4o Audio Previewvoice: Alloy· EmergentTTS-Eval data | 14.7% |
| 11 | Gemini 2.5 Pro TTSvoice: Zephyr, strong-prompt· EmergentTTS-Eval data | 16.2% |
| 12 | Kokoro 82Mvoice: af_heart· EmergentTTS-Eval data | 22.2% |
| 13 | Orpheus TTSvoice: Tara· EmergentTTS-Eval data | 22.3% |
| 14 | F5 TTSvoice: basic_ref_en· EmergentTTS-Eval data | 23.5% |
Data credits: EmergentTTS-Eval (Boson AI), Apache-2.0 (licence)