Book a demo
Feedback
Overview
Analysis
Ranking Evaluation!
Loading...
Loading...
Question 1. Listen to the two audio samples and rate which one sounds more natural.
Comparison | 5 steps
Overall
5 models, 25 groups, 300 matches
Filter
Model A
Model B
1
2
3
4
5
1. Cartesia - sonic-3
–
0.45
0.50
0.67
0.15
2. ElevenLabs - eleven_v3
0.55
–
0.07
0.38
0.19
3. Google Cloud - Chirp3-HD
0.50
0.93
–
0.60
0.38
4. OpenAI - gpt-4o-mini-tts
0.33
0.62
0.40
–
0.18
5. Rime - arcana
0.85
0.81
0.62
0.82
–
1
0.75
0.5
0.25
0
Question 2. Listen to the speech/audio samples and rate which one you prefer.
Comparison | 5 steps
Overall
5 models, 24 groups, 300 matches
Filter
Model A
Model B
1
2
3
4
5
1. Cartesia - sonic-3
–
0.62
0.26
0.44
0.35
2. ElevenLabs - eleven_v3
0.38
–
0.44
0.36
0.17
3. Google Cloud - Chirp3-HD
0.74
0.56
–
0.50
0.61
4. OpenAI - gpt-4o-mini-tts
0.56
0.64
0.50
–
0.33
5. Rime - arcana
0.65
0.83
0.39
0.67
–
1
0.75
0.5
0.25
0
