realism-final

Final realism head-to-head: karen (F) and rv_M_147306_2 (M), the two best-performing Bland voices from the picker run, vs ElevenLabs v3 and Grok.

Overall

competitor (Model B)

1.32

bland (Model A)

By Tag

competitor (Model B)

bland (Model A)

Answers

2. bland (Model A) sounds more human

-1

-2. competitor (Model B) sounds more human

658 (54.83%)

339 (28.25%)

142 (11.83%)

48 (4.00%)

13 (1.08%)

Deep analysis

2. bland (Model A) sounds more human

-1

-2. competitor (Model B) sounds more human

		Tags	Statistics
00:00 --:-- rv_M_147306_2_10.wav 00:00 --:-- ev3_mark_10.wav	bland competitor	rv_M_147306_2__vs__ev3_mark__10 rv_M_147306_2 M s10 rv_M_147306_2__vs__ev3_mark__10 ev3_mark M s10	0.50 1.13 0.50
00:00 --:-- karen_11.wav 00:00 --:-- ev3_jessica_11.wav	bland competitor	karen__vs__ev3_jessica__11 karen F s11 karen__vs__ev3_jessica__11 ev3_jessica F s11	0.90 0.86 0.38
00:00 --:-- rv_M_147306_2_11.wav 00:00 --:-- grok_altair_11.wav	bland competitor	rv_M_147306_2__vs__grok_altair__11 rv_M_147306_2 M s11 rv_M_147306_2__vs__grok_altair__11 grok_altair M s11	0.90 0.92 0.41
00:00 --:-- karen_15.wav 00:00 --:-- ev3_jessica_15.wav	bland competitor	karen__vs__ev3_jessica__15 karen F s15 karen__vs__ev3_jessica__15 ev3_jessica F s15	1.60 0.50 0.22
00:00 --:-- karen_01.wav 00:00 --:-- ev3_jessica_01.wav	bland competitor	karen__vs__ev3_jessica__01 karen F s01 karen__vs__ev3_jessica__01 ev3_jessica F s01	1.60 0.37 0.16
00:00 --:-- karen_16.wav 00:00 --:-- ev3_jessica_16.wav	bland competitor	karen__vs__ev3_jessica__16 karen F s16 karen__vs__ev3_jessica__16 ev3_jessica F s16	0.80 1.00 0.44
00:00 --:-- rv_M_147306_2_05.wav 00:00 --:-- grok_altair_05.wav	bland competitor	rv_M_147306_2__vs__grok_altair__05 rv_M_147306_2 M s05 rv_M_147306_2__vs__grok_altair__05 grok_altair M s05	1.20 0.74 0.33
00:00 --:-- karen_25.wav 00:00 --:-- grok_carina_25.wav	bland competitor	karen__vs__grok_carina__25 karen F s25 karen__vs__grok_carina__25 grok_carina F s25	0.90 0.92 0.41

Overall

competitor (Model B)

1.32

bland (Model A)

By Tag

competitor (Model B)

bland (Model A)

Answers

2. bland (Model A) sounds more human

-1

-2. competitor (Model B) sounds more human

658 (54.83%)

339 (28.25%)

142 (11.83%)

48 (4.00%)

13 (1.08%)

Deep analysis

2. bland (Model A) sounds more human

-1

-2. competitor (Model B) sounds more human

		Tags	Statistics
00:00 --:-- rv_M_147306_2_10.wav 00:00 --:-- ev3_mark_10.wav	bland competitor	rv_M_147306_2__vs__ev3_mark__10 rv_M_147306_2 M s10 rv_M_147306_2__vs__ev3_mark__10 ev3_mark M s10	0.50 1.13 0.50
00:00 --:-- karen_11.wav 00:00 --:-- ev3_jessica_11.wav	bland competitor	karen__vs__ev3_jessica__11 karen F s11 karen__vs__ev3_jessica__11 ev3_jessica F s11	0.90 0.86 0.38
00:00 --:-- rv_M_147306_2_11.wav 00:00 --:-- grok_altair_11.wav	bland competitor	rv_M_147306_2__vs__grok_altair__11 rv_M_147306_2 M s11 rv_M_147306_2__vs__grok_altair__11 grok_altair M s11	0.90 0.92 0.41
00:00 --:-- karen_15.wav 00:00 --:-- ev3_jessica_15.wav	bland competitor	karen__vs__ev3_jessica__15 karen F s15 karen__vs__ev3_jessica__15 ev3_jessica F s15	1.60 0.50 0.22
00:00 --:-- karen_01.wav 00:00 --:-- ev3_jessica_01.wav	bland competitor	karen__vs__ev3_jessica__01 karen F s01 karen__vs__ev3_jessica__01 ev3_jessica F s01	1.60 0.37 0.16
00:00 --:-- karen_16.wav 00:00 --:-- ev3_jessica_16.wav	bland competitor	karen__vs__ev3_jessica__16 karen F s16 karen__vs__ev3_jessica__16 ev3_jessica F s16	0.80 1.00 0.44
00:00 --:-- rv_M_147306_2_05.wav 00:00 --:-- grok_altair_05.wav	bland competitor	rv_M_147306_2__vs__grok_altair__05 rv_M_147306_2 M s05 rv_M_147306_2__vs__grok_altair__05 grok_altair M s05	1.20 0.74 0.33
00:00 --:-- karen_25.wav 00:00 --:-- grok_carina_25.wav	bland competitor	karen__vs__grok_carina__25 karen F s25 karen__vs__grok_carina__25 grok_carina F s25	0.90 0.92 0.41