Book a demo
Feedback
Overview
Analysis
US English naturalness comparison
Naturalness comparison of Cartesia, Open AI, PlayAI, Eleven Labs for American English. For each model, we use male/female voices.
Loading...
Loading...
Question 1. Listen to the speech samples and rate how natural they sound.
Single select | Scored | 5 radio buttons
Overall
MAX 5
Excellent
4
Good
3
Fair
2
Poor
MIN 1
Bad
MAX 5
Excellent
4
Good
3
Fair
2
Poor
MIN 1
Bad
Models
By Tag
Model
Tag
MAX 5
Excellent
4
Good
3
Fair
2
Poor
MIN 1
Bad
MAX 5
Excellent
4
Good
3
Fair
2
Poor
MIN 1
Bad
Cartesia
Eleven Labs
OpenAI
Play AI
Tags
Answers
5. Excellent
4. Good
3. Fair
2. Poor
1. Bad
Cartesia
Eleven Labs
OpenAI
Play AI
27 (7.94%)
147 (43.24%)
109 (32.06%)
38 (11.18%)
19 (5.59%)
80 (23.53%)
153 (45.00%)
78 (22.94%)
28 (8.24%)
1 (0.29%)
89 (26.18%)
169 (49.71%)
53 (15.59%)
22 (6.47%)
7 (2.06%)
36 (10.59%)
111 (32.65%)
116 (34.12%)
69 (20.29%)
8 (2.35%)
5. Excellent
4. Good
3. Fair
2. Poor
1. Bad
Tags
All tags
Cartesia
Eleven Labs
OpenAI
Play AI
27 (7.94%)
80 (23.53%)
89 (26.18%)
36 (10.59%)
Deep analysis
Distribution
Mean
Files
5. Excellent
4. Good
3. Fair
2. Poor
1. Bad
MAX 5
4
3
2
MIN 1
MAX 5
4
3
2
MIN 1
Models: All models
Tags: All tags
Filename
Model
Tags
Statistics
x̅
CI
σ
x̅
00:00
--:--
cartesia/speech_us_0.mp3
Cartesia
Man
Narrative
x̅
3.80
CI
0.74
σ
x̅
0.33
00:00
--:--
elevenlabs/speech_us_0.mp3
Eleven Labs
Man
Narrative
x̅
4.20
CI
0.74
σ
x̅
0.33
00:00
--:--
openai/speech_us_0.mp3
OpenAI
Man
Narrative
x̅
3.70
CI
0.83
σ
x̅
0.37
00:00
--:--
playai/speech_us_0_William.wav
Play AI
Man
Narrative
x̅
3.70
CI
0.59
σ
x̅
0.26
00:00
--:--
cartesia/speech_us_1.mp3
Cartesia
Woman
Narrative
x̅
3.80
CI
0.81
σ
x̅
0.36
00:00
--:--
elevenlabs/speech_us_1.mp3
Eleven Labs
Woman
Narrative
x̅
3.80
CI
0.45
σ
x̅
0.20
00:00
--:--
openai/speech_us_1.mp3
OpenAI
Woman
Narrative
x̅
3.60
CI
0.60
σ
x̅
0.27
00:00
--:--
playai/speech_us_1_Samantha.wav
Play AI
Woman
Narrative
x̅
3.70
CI
0.59
σ
x̅
0.26
1
2
3
4
5
...
17
Question 2. Tell us about the pronunciation accuracy, contextual relevancy of this audio sample (Select all that apply)
Multiple select | No-scored | 5 checkboxes
Answers
A1. Inaccurate pronunciation
A2. Some words are not spoken
A3. The speaking tone isn't well aligned with the context
A4. The speech is too slow or too fast
A5. Sudden changes in emotion
Cartesia
Eleven Labs
OpenAI
Play AI
62 (13.60%)
11 (2.41%)
151 (33.11%)
174 (38.16%)
58 (12.72%)
35 (9.28%)
33 (8.75%)
104 (27.59%)
165 (43.77%)
40 (10.61%)
25 (5.92%)
6 (1.42%)
159 (37.68%)
167 (39.57%)
65 (15.40%)
21 (5.45%)
32 (8.31%)
107 (27.79%)
181 (47.01%)
44 (11.43%)
A1. Inaccurate pronunciation
A2. Some words are not spoken
A3. The speaking tone isn't well aligned with the context
A4. The speech is too slow or too fast
A5. Sudden changes in emotion
Tags
All tags
Cartesia
Eleven Labs
OpenAI
Play AI
62 (13.60%)
35 (9.28%)
25 (5.92%)
21 (5.45%)
Deep analysis
Distribution
Files
A1. Inaccurate pronunciation
A2. Some words are not spoken
A3. The speaking tone isn't well aligned with the context
A4. The speech is too slow or too fast
A5. Sudden changes in emotion
Models: All models
Tags: All tags
Answers
Inaccurate pronunciation
Some words are not spoken
The speaking tone isn't well aligned with the context
The speech is too slow or too fast
Sudden changes in emotion
Filename
Model
Tags
00:00
--:--
cartesia/speech_us_0.mp3
Cartesia
Man
Narrative
Sudden changes in emotion
The speaking tone isn't well aligned with the context
The speech is too slow or too fast
00:00
--:--
elevenlabs/speech_us_0.mp3
Eleven Labs
Man
Narrative
The speech is too slow or too fast
Inaccurate pronunciation
Some words are not spoken
2 more...
00:00
--:--
openai/speech_us_0.mp3
OpenAI
Man
Narrative
The speaking tone isn't well aligned with the context
Sudden changes in emotion
Some words are not spoken
1 more...
00:00
--:--
playai/speech_us_0_William.wav
Play AI
Man
Narrative
The speech is too slow or too fast
Some words are not spoken
The speaking tone isn't well aligned with the context
1 more...
00:00
--:--
cartesia/speech_us_1.mp3
Cartesia
Woman
Narrative
Sudden changes in emotion
The speech is too slow or too fast
The speaking tone isn't well aligned with the context
1 more...
00:00
--:--
elevenlabs/speech_us_1.mp3
Eleven Labs
Woman
Narrative
The speech is too slow or too fast
Inaccurate pronunciation
The speaking tone isn't well aligned with the context
2 more...
00:00
--:--
openai/speech_us_1.mp3
OpenAI
Woman
Narrative
Sudden changes in emotion
Inaccurate pronunciation
The speech is too slow or too fast
1 more...
00:00
--:--
playai/speech_us_1_Samantha.wav
Play AI
Woman
Narrative
The speaking tone isn't well aligned with the context
Inaccurate pronunciation
Sudden changes in emotion
1 more...
1
2
3
4
5
...
17
Question 3. Tell us about the quality of this audio sample (Select all that apply)
Multiple select | No-scored | 5 checkboxes
Answers
A1. Background noise
A2. Inconsistent volume (e.g., too loud or too soft)
A3. Cut out or drop abruptly at times
A4. Distorted audio affecting quality (hoarse, metallic, or crackling voice)
A5. Unrelated noise (clicks, beeps, unnatural lip noises)
Cartesia
Eleven Labs
OpenAI
Play AI
32 (7.55%)
138 (32.55%)
51 (12.03%)
134 (31.60%)
69 (16.27%)
12 (3.24%)
156 (42.16%)
84 (22.70%)
88 (23.78%)
30 (8.11%)
4 (1.08%)
141 (38.01%)
45 (12.13%)
124 (33.42%)
57 (15.36%)
15 (3.70%)
135 (33.33%)
88 (21.73%)
139 (34.32%)
28 (6.91%)
A1. Background noise
A2. Inconsistent volume (e.g., too loud or too soft)
A3. Cut out or drop abruptly at times
A4. Distorted audio affecting quality (hoarse, metallic, or crackling voice)
A5. Unrelated noise (clicks, beeps, unnatural lip noises)
Tags
All tags
Cartesia
Eleven Labs
OpenAI
Play AI
32 (7.55%)
12 (3.24%)
4 (1.08%)
15 (3.70%)
Deep analysis
Distribution
Files
A1. Background noise
A2. Inconsistent volume (e.g., too loud or too soft)
A3. Cut out or drop abruptly at times
A4. Distorted audio affecting quality (hoarse, metallic, or crackling voice)
A5. Unrelated noise (clicks, beeps, unnatural lip noises)
Models: All models
Tags: All tags
Answers
Background noise
Inconsistent volume (e.g., too loud or too soft)
Cut out or drop abruptly at times
Distorted audio affecting quality (hoarse, metallic, or crackling voice)
Unrelated noise (clicks, beeps, unnatural lip noises)
Filename
Model
Tags
00:00
--:--
cartesia/speech_us_0.mp3
Cartesia
Man
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Unrelated noise (clicks, beeps, unnatural lip noises)
2 more...
00:00
--:--
elevenlabs/speech_us_0.mp3
Eleven Labs
Man
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Distorted audio affecting quality (hoarse, metallic, or crackling voice)
2 more...
00:00
--:--
openai/speech_us_0.mp3
OpenAI
Man
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Unrelated noise (clicks, beeps, unnatural lip noises)
1 more...
00:00
--:--
playai/speech_us_0_William.wav
Play AI
Man
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Unrelated noise (clicks, beeps, unnatural lip noises)
2 more...
00:00
--:--
cartesia/speech_us_1.mp3
Cartesia
Woman
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Unrelated noise (clicks, beeps, unnatural lip noises)
1 more...
00:00
--:--
elevenlabs/speech_us_1.mp3
Eleven Labs
Woman
Narrative
Inconsistent volume (e.g., too loud or too soft)
Cut out or drop abruptly at times
Background noise
1 more...
00:00
--:--
openai/speech_us_1.mp3
OpenAI
Woman
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Unrelated noise (clicks, beeps, unnatural lip noises)
1 more...
00:00
--:--
playai/speech_us_1_Samantha.wav
Play AI
Woman
Narrative
Cut out or drop abruptly at times
Inconsistent volume (e.g., too loud or too soft)
Distorted audio affecting quality (hoarse, metallic, or crackling voice)
1 more...
1
2
3
4
5
...
17
Annotations (beta)
Annotations (beta)
Q5
Q9
Q21
Q53
Q61
Q85
Q97
Q109
Q125
Q133
Q1
Q13
Q17
Q25
Q29
Q33
Q37
Q41
Q45
Q49
Q57
Q65
Q69
Q73
Q77
Q81
Q89
Q93
Q101
Q105
Q113
Q117
Q121
Q129
Q2
Q6
Q10
Q14
Q18
Q22
Q26
Q30
Q34
Q38
Q42
Q46
Q50
Q54
Q58
Q62
Q66
Q70
Q74
Q78
Q82
Q86
Q90
Q94
Q98
Q102
Q106
Q110
Q114
Q118
Q122
Q126
Q130
Q134
Q11
Q15
Q27
Q43
Q47
Q63
Q75
Q127
Q3
Q7
Q19
Q23
Q31
Q35
Q39
Q51
Q55
Q59
Q67
Q71
Q79
Q83
Q87
Q91
Q95
Q99
Q103
Q107
Q111
Q115
Q119
Q123
Q131
Q135
Q4
Q8
Q12
Q16
Q20
Q24
Q28
Q32
Q36
Q40
Q44
Q48
Q52
Q56
Q60
Q64
Q68
Q72
Q76
Q80
Q84
Q88
Q92
Q96
Q100
Q104
Q108
Q112
Q116
Q120
Q124
Q128
Q132
Q136
