Book a demo
Feedback
Overview
Analysis
Play (Dialog) vs Eleven Labs (Multilingual V2)
Preference across 60 sample pairs
Loading...
Loading...
Question 1. Listen to the speech/audio samples and rate which one you prefer.
Comparison | 5 steps
Overall
Dialog (Model B)
-0.41
Multilingual V2 (Model A)
Answers
2
.
Multilingual V2 (Model A)
is better
1
0
-1
-2
.
Dialog (Model B)
is better
1379 (22.98%)
690 (11.50%)
492 (8.20%)
960 (16.00%)
2479 (41.32%)
Deep analysis
Distribution
Mean
Files
2
.
Multilingual V2 (Model A)
is better
1
0
-1
-2
.
Dialog (Model B)
is better
MAX 2
1
0
-1
MIN -2
MAX 2
1
0
-1
MIN -2
Tags
Filename
Model
Tags
Statistics
x̅
CI
σ
x̅
00:00
--:--
30.wav
00:00
--:--
30.wav
Multilingual V2
Dialog
x̅
0.09
CI
0.34
σ
x̅
0.17
00:00
--:--
31.wav
00:00
--:--
31.wav
Multilingual V2
Dialog
x̅
-0.68
CI
0.32
σ
x̅
0.16
00:00
--:--
32.wav
00:00
--:--
32.wav
Multilingual V2
Dialog
x̅
0.41
CI
0.32
σ
x̅
0.16
00:00
--:--
33.wav
00:00
--:--
33.wav
Multilingual V2
Dialog
x̅
-0.50
CI
0.32
σ
x̅
0.16
00:00
--:--
34.wav
00:00
--:--
34.wav
Multilingual V2
Dialog
x̅
-1.15
CI
0.26
σ
x̅
0.13
00:00
--:--
35.wav
00:00
--:--
35.wav
Multilingual V2
Dialog
x̅
0.48
CI
0.31
σ
x̅
0.16
00:00
--:--
36.wav
00:00
--:--
36.wav
Multilingual V2
Dialog
x̅
-0.32
CI
0.35
σ
x̅
0.17
00:00
--:--
37.wav
00:00
--:--
37.wav
Multilingual V2
Dialog
x̅
-0.94
CI
0.28
σ
x̅
0.14
1
2
3
4
5
...
8
Question 2. Listen to the two audio samples and rate which one sounds more natural.
Comparison | 5 steps
Overall
Dialog (Model B)
-0.50
Multilingual V2 (Model A)
Answers
2
.
Multilingual V2 (Model A)
is better
1
0
-1
-2
.
Dialog (Model B)
is better
1164 (19.40%)
686 (11.43%)
629 (10.48%)
1034 (17.23%)
2487 (41.45%)
Deep analysis
Distribution
Mean
Files
2
.
Multilingual V2 (Model A)
is better
1
0
-1
-2
.
Dialog (Model B)
is better
MAX 2
1
0
-1
MIN -2
MAX 2
1
0
-1
MIN -2
Tags
Filename
Model
Tags
Statistics
x̅
CI
σ
x̅
00:00
--:--
30.wav
00:00
--:--
30.wav
Multilingual V2
Dialog
x̅
-0.23
CI
0.35
σ
x̅
0.17
00:00
--:--
31.wav
00:00
--:--
31.wav
Multilingual V2
Dialog
x̅
-0.77
CI
0.30
σ
x̅
0.15
00:00
--:--
32.wav
00:00
--:--
32.wav
Multilingual V2
Dialog
x̅
0.59
CI
0.32
σ
x̅
0.16
00:00
--:--
33.wav
00:00
--:--
33.wav
Multilingual V2
Dialog
x̅
-0.62
CI
0.31
σ
x̅
0.16
00:00
--:--
34.wav
00:00
--:--
34.wav
Multilingual V2
Dialog
x̅
-1.36
CI
0.22
σ
x̅
0.11
00:00
--:--
35.wav
00:00
--:--
35.wav
Multilingual V2
Dialog
x̅
0.53
CI
0.32
σ
x̅
0.16
00:00
--:--
36.wav
00:00
--:--
36.wav
Multilingual V2
Dialog
x̅
-0.42
CI
0.34
σ
x̅
0.17
00:00
--:--
37.wav
00:00
--:--
37.wav
Multilingual V2
Dialog
x̅
-0.94
CI
0.28
σ
x̅
0.14
1
2
3
4
5
...
8
Question 3. What was the main factor behind your preferred sample?
Multiple select | No-scored | 5 checkboxes
Answers
A1. Expressiveness
A2. Audio quality
A3. Pacing (e.g. rhythm, tempo, speed)
A4. Voice accuracy (e.g. pronounciation)
A5. Hallucinations (e.g. random noises or utterances)
4061 (36.52%)
1662 (14.94%)
3597 (32.34%)
1364 (12.27%)
437 (3.93%)
Deep analysis
Distribution
Files
A1. Expressiveness
A2. Audio quality
A3. Pacing (e.g. rhythm, tempo, speed)
A4. Voice accuracy (e.g. pronounciation)
A5. Hallucinations (e.g. random noises or utterances)
Tags
Answers
Expressiveness
Audio quality
Pacing (e.g. rhythm, tempo, speed)
Voice accuracy (e.g. pronounciation)
Hallucinations (e.g. random noises or utterances)
Filename
Model
Tags
00:00
--:--
30.wav
00:00
--:--
30.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Voice accuracy (e.g. pronounciation)
2 more...
00:00
--:--
31.wav
00:00
--:--
31.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Audio quality
2 more...
00:00
--:--
32.wav
00:00
--:--
32.wav
Multilingual V2
Dialog
Expressiveness
Audio quality
Pacing (e.g. rhythm, tempo, speed)
1 more...
00:00
--:--
33.wav
00:00
--:--
33.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Voice accuracy (e.g. pronounciation)
2 more...
00:00
--:--
34.wav
00:00
--:--
34.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Audio quality
2 more...
00:00
--:--
35.wav
00:00
--:--
35.wav
Multilingual V2
Dialog
Voice accuracy (e.g. pronounciation)
Audio quality
Hallucinations (e.g. random noises or utterances)
2 more...
00:00
--:--
36.wav
00:00
--:--
36.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Audio quality
2 more...
00:00
--:--
37.wav
00:00
--:--
37.wav
Multilingual V2
Dialog
Expressiveness
Pacing (e.g. rhythm, tempo, speed)
Audio quality
2 more...
1
2
3
4
5
...
8
