Controlled Voice Arena LeaderboardArtificial Analysis

Compare Text to Speech (TTS) models using the same 8 cloned voices (4 US, 4 UK).

Range
Model
Elo
Samples
Released
Pricing 1
11-2
HeyGen logo
HeyGen Voice
1188±1395% interval 1175 to 1201
2,356Oct 2026$30.00 /1M chars
21-3
Alibaba logo
Qwen-Audio-3.1-TTS-Plus
1180±1395% interval 1167 to 1193
2,691Sept 2026$19.31 /1M chars
32-3
HeyGen logo
HeyGen Voice Turbo
1172±1695% interval 1156 to 1188
2,172Oct 2026$4.00 /1M chars
44-7
ElevenLabs logo
Eleven v4 Turbo
1153±1295% interval 1141 to 1165
3,071Sept 2026$40.00 /1M chars
54-7
ElevenLabs logo
Eleven v4
1153±1295% interval 1141 to 1165
3,008Sept 2026$80.00 /1M chars
64-7
Cartesia logo
Sonic 3.6
1147±1295% interval 1135 to 1159
3,798Aug 2026$49.00 /1M chars
74-7
Inworld logo
Realtime TTS-2
1145±1295% interval 1133 to 1157
3,610Aug 2026$20.83 /1M chars
88
Alibaba logo
Qwen-Audio-3.0-TTS-Plus
1128±1295% interval 1116 to 1140
3,438Sept 2026$19.31 /1M chars
99
Cartesia logo
Sonic 3.5
1116±1195% interval 1105 to 1127
5,911May 2026$49.00 /1M chars
1010-11
Smallest.ai logo
Lightning V3.1 Pro (Oct 2026)
1100±1595% interval 1085 to 1115
2,120Oct 2026$19.50 /1M chars
1110-12
AssemblyAI logo
AssemblyAI-TTS-1
1091±1595% interval 1076 to 1106
2,017Oct 2026$15.00 /1M chars
1211-15
SpeechifyAI logo
Simba 3.2
1083±1295% interval 1071 to 1095
3,500Jul 2026$6.58 /1M chars
1312-21
Fish Audio logo
Fish Audio Drama 3Hugging Face
1075±1595% interval 1060 to 1090
2,121Oct 2026$15.00 /1M chars
1412-19
ElevenLabs logo
Eleven v3
1074±1195% interval 1063 to 1085
5,014Feb 2026$100.00 /1M chars
1512-19
StepFun logo
StepAudio 2.5 TTS
1074±1195% interval 1063 to 1085
4,397Apr 2026$85.00 /1M chars
1612-22
Mistral logo
Voxtral 3 TTS
1069±1595% interval 1054 to 1084
2,290Oct 2026$13.00 /1M chars
1713-22
Ant Group logo
Ming-3.0-ttsHugging Face
1067±1495% interval 1053 to 1081
2,429Oct 2026N/A
1813-21
Inworld logo
Realtime TTS-2 Flash
1066±1295% interval 1054 to 1078
3,758Aug 2026$10.42 /1M chars
1913-22
ElevenLabs logo
v3 Conversational
1065±1295% interval 1053 to 1077
3,268Aug 2026$50.00 /1M chars
2014-24
Fish Audio logo
Fish Audio Drama 3 PreviewHugging Face
1062±1395% interval 1049 to 1075
2,670Oct 2026$15.00 /1M chars
2116-24
SpaceXAI logo
SpaceXAI TTS
1061±1295% interval 1049 to 1073
3,950Mar 2026$15.00 /1M chars
2219-24
Gradium logo
Gradium TTS (Sep 2026)
1054±1295% interval 1042 to 1066
2,825Sept 2026$47.78 /1M chars
2320-24
Google logo
Gemini 3.8 Flash TTS
1052±1295% interval 1040 to 1064
3,479Sept 2026$16.49 /1M chars
2420-25
Google logo
Gemini 3.8 Flash-Lite TTS
1052±1295% interval 1040 to 1064
3,596Sept 2026$11.03 /1M chars
2524-25
SpeechifyAI logo
Simba 3.0
1040±1295% interval 1028 to 1052
3,695Feb 2026$6.58 /1M chars
2626-29
MiniMax logo
Speech 2.8 HD
1024±1295% interval 1012 to 1036
4,175Feb 2026$100.00 /1M chars
2726-29
MiniMax logo
Speech 2.8 Turbo
1023±1195% interval 1012 to 1034
4,535Feb 2026$60.00 /1M chars
2826-32
BreezeBlue logo
Breeze TTS 2Hugging Face
1020±1295% interval 1008 to 1032
3,043Aug 2026$34.00 /1M chars
2926-32
Gradium logo
Gradium TTS (Aug 2026)
1019±1295% interval 1007 to 1031
2,986Aug 2026$47.22 /1M chars
3028-34
Fish Audio logo
Fish Audio S2 ProHugging Face
1011±1195% interval 1000 to 1022
5,033Mar 2026$15.00 /1M chars
3127-35
Fish Audio logo
Fish Audio S2.1 Pro (Oct 2026)
1010±1395% interval 997 to 1023
2,364Oct 2026$15.00 /1M chars
3228-35
Mistral logo
Voxtral TTSHugging Face
1008±1295% interval 996 to 1020
3,290Mar 2026$16.00 /1M chars
3329-35
Fish Audio logo
OpenAudio S1 MiniHugging Face
1006±1395% interval 993 to 1019
3,180Jun 2025$15.00 /1M chars
3430-35
ElevenLabs logo
Multilingual v2
1002±1295% interval 990 to 1014
4,169Aug 2023$100.00 /1M chars
3535
Fish Audio logo
OpenAudio S1
1000AnchorFixed at 1000 as the reference point for this board's Elo scale.
7,053Jun 2025$15.00 /1M chars
3635-38
ElevenLabs logo
Flash v2.5
989±1295% interval 977 to 1001
4,171Dec 2024$50.00 /1M chars
3736-38
Fish Audio logo
Fish Audio S1
987±1295% interval 975 to 999
4,007Oct 2025$15.00 /1M chars
3836-38
ElevenLabs logo
Turbo v2.5
983±1395% interval 970 to 996
3,057Jul 2024$50.00 /1M chars
3939-42
KugelAudio logo
Kugel 3
969±1295% interval 957 to 981
4,395Jun 2026N/A
4039-42
Boson AI logo
Higgs Audio V3 TTSHugging Face
965±1395% interval 952 to 978
2,833Jun 2026$15.00 /1M chars
4139-42
Soniox logo
Soniox TTS Real-Time v2
963±1395% interval 950 to 976
2,566Aug 2026$14.23 /1M chars
4239-42
Cartesia logo
Sonic 3
959±1395% interval 946 to 972
2,993Oct 2025$49.00 /1M chars
4342-46
NVIDIA logo
Magpie TTS Zeroshot
943±1795% interval 926 to 960
1,060Jul 2026N/A
4443-45
Resemble AI logo
ChatterboxGitHub
941±1395% interval 928 to 954
2,938May 2025$25.00 /1M chars
4543-46
Krafton logo
Raon SpeechLM
933±1395% interval 920 to 946
2,513Apr 2026N/A
4644-46
Noiz logo
Noiz TTS
928±1495% interval 914 to 942
2,556Nov 2025N/A
4747
Smallest.ai logo
Lightning v3.1
889±1495% interval 875 to 903
2,622Mar 2026$25.00 /1M chars
4848
Coqui logo
XTTS v2Hugging Face
850±1595% interval 835 to 865
2,736Nov 2023$40.44 /1M chars
4949
OpenVoice logo
OpenVoice v2Hugging Face
825±1695% interval 809 to 841
2,351Apr 2024$8.33 /1M chars

1 API Pricing reflects the cost to generate 1M characters on the model creator's API with the model's default settings

2 Open Weights includes models that can be self-hosted using downloadable model weights or a provider-supplied inference runtime. Open Weights Commercial includes models whose published license permits commercial use, including use subject to license conditions (e.g. an NVIDIA AI Enterprise subscription), and excludes models that require a separately negotiated commercial agreement.