Voice Cloning on Common Voice English
0.81SIM ScoreChroma 1.0
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Chroma 1.0zero-shot=true, sampling rate=24kHz2026.01 | 0.81 | — | — | |
| Seed-TTSzero-shot=true, sampling rate=16kHz2026.01 | 0.76 | — | — | |
| Human Baselinezero-shot=true2026.01 | 0.73 | — | — | |
| CosyVoice 3zero-shot=true, sampling rate=16kHz2026.01 | 0.72 | — | — | |
| FireRedTTS-2zero-shot=true, sampling rate=16kHz2026.01 | 0.66 | — | — | |
| Step-Audio-TTSzero-shot=true, sampling rate=16kHz2026.01 | 0.66 | — | — | |
| F5-TTSzero-shot=true, sampling rate=16kHz2026.01 | 0.64 | — | — | |
| Chroma 1.0Sampling rate=24kHz, Evaluation Protocol=Subjective preference comparison, Setting=Zero-shot2026.01 | — | 24.4 | 40.6 | |
| ElevenLabsAPI version=eleven_multilingual_v2, Evaluation Protocol=Subjective preference comparison, Setting=Zero-shot2026.01 | — | 57.2 | 42.4 |