Text-to-Speech on InstructTTSEval EN
92.3APSGemini-flash
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini-flash2026.01 | 92.3 | 93.8 | 80.1 | — | |
| Gemini-pro2026.01 | 87.6 | 86 | 67.2 | — | |
| Hume2026.01 | 83 | 75.3 | 54.3 | — | |
| Qwen3TTS-12Hz-1.7B-VDFrame rate=12Hz, Parameters=1.7B2026.01 | 82.9 | 82.4 | 68.4 | — | |
| MiMo-Audio-7B-Instruct2025.12 | 80.6 | 77.63 | 59.54 | 72.59 | |
| Mimo-Audio-7B-InstructParameters=7B2026.01 | 80.6 | 77.6 | 59.5 | — | |
| Qwen3TTS-25Hz-1.7B-CustomVoiceFrame rate=25Hz, Parameters=1.7B2026.01 | 79 | 82.8 | 69.3 | — | |
| Qwen3TTS-12Hz-1.7B-CustomVoiceFrame rate=12Hz, Parameters=1.7B2026.01 | 77.3 | 77.1 | 63.7 | — | |
| GPT-4o-mini-tts2025.12 | 76.4 | 74.3 | 54.8 | 68.5 | |
| GPT-4o-mini-tts2026.01 | 76.4 | 74.3 | 54.8 | — | |
| PromptTTS2026.01 | 64.3 | 47.2 | 31.4 | — | |
| Parler-tts-miniSize=mini2026.01 | 63.4 | 48.7 | 28.6 | — | |
| Parler-tts-largeSize=large2026.01 | 60 | 45.9 | 31.2 | — | |
| PromptStyle2026.01 | 57.4 | 46.4 | 30.9 | — | |
| VoxInstruct2026.01 | 54.9 | 57 | 39.3 | — |