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 | |
|---|---|---|---|---|---|---|
| 1 | 1-2 |  HeyGen Voice | 1189±1395% interval 1176 to 1202 | 2,414 | Oct 2026 | $30.00 /1M chars |
| 2 | 1-3 |  Qwen-Audio-3.1-TTS-Plus | 1179±1395% interval 1166 to 1192 | 2,756 | Sept 2026 | $19.31 /1M chars |
| 3 | 1-3 | HeyGen Voice Turbo | 1173±1695% interval 1157 to 1189 | 2,235 | Oct 2026 | $4.00 /1M chars |
| 4 | 4-7 |  Eleven v4 | 1153±1295% interval 1141 to 1165 | 3,061 | Sept 2026 | $80.00 /1M chars |
| 5 | 4-7 | Eleven v4 Turbo | 1153±1295% interval 1141 to 1165 | 3,124 | Sept 2026 | $40.00 /1M chars |
| 6 | 4-7 |  Sonic 3.6 | 1147±1295% interval 1135 to 1159 | 3,853 | Aug 2026 | $49.00 /1M chars |
| 7 | 4-7 |  Realtime TTS-2 | 1143±1295% interval 1131 to 1155 | 3,664 | Aug 2026 | $20.83 /1M chars |
| 8 | 8-9 | Qwen-Audio-3.0-TTS-Plus | 1128±1295% interval 1116 to 1140 | 3,478 | Sept 2026 | $19.31 /1M chars |
| 9 | 9 | Sonic 3.5 | 1117±1195% interval 1106 to 1128 | 5,959 | May 2026 | $49.00 /1M chars |
| 10 | 10-11 |  Lightning V3.1 Pro (Oct 2026) | 1100±1595% interval 1085 to 1115 | 2,159 | Oct 2026 | $19.50 /1M chars |
| 11 | 10-14 |  AssemblyAI-TTS-1 | 1089±1595% interval 1074 to 1104 | 2,052 | Oct 2026 | $15.00 /1M chars |
| 12 | 11-15 |  Simba 3.2 | 1082±1295% interval 1070 to 1094 | 3,540 | Jul 2026 | $6.58 /1M chars |
| 13 | 12-18 | Eleven v3 | 1076±1195% interval 1065 to 1087 | 5,046 | Feb 2026 | $100.00 /1M chars |
| 14 | 12-19 |  StepAudio 2.5 TTS | 1075±1195% interval 1064 to 1086 | 4,415 | Apr 2026 | $85.00 /1M chars |
| 15 | 12-21 |  Fish Audio Drama 3  | 1073±1595% interval 1058 to 1088 | 2,167 | Oct 2026 | $15.00 /1M chars |
| 16 | 13-21 | Realtime TTS-2 Flash | 1068±1295% interval 1056 to 1080 | 3,785 | Aug 2026 | $10.42 /1M chars |
| 17 | 13-23 |  Ming-3.0-tts | 1067±1495% interval 1053 to 1081 | 2,469 | Oct 2026 | N/A |
| 18 | 13-23 |  Voxtral 3 TTS | 1067±1495% interval 1053 to 1081 | 2,329 | Oct 2026 | $13.00 /1M chars |
| 19 | 13-23 | v3 Conversational | 1065±1295% interval 1053 to 1077 | 3,310 | Aug 2026 | $50.00 /1M chars |
| 20 | 16-24 |  SpaceXAI TTS | 1061±1195% interval 1050 to 1072 | 3,989 | Mar 2026 | $15.00 /1M chars |
| 21 | 16-24 | Fish Audio Drama 3 Preview | 1060±1395% interval 1047 to 1073 | 2,705 | Oct 2026 | $15.00 /1M chars |
| 22 | 19-24 |  Gradium TTS (Sep 2026) | 1055±1295% interval 1043 to 1067 | 2,856 | Sept 2026 | $47.78 /1M chars |
| 23 | 19-24 |  Gemini 3.8 Flash TTS | 1053±1295% interval 1041 to 1065 | 3,512 | Sept 2026 | $16.49 /1M chars |
| 24 | 20-24 | Gemini 3.8 Flash-Lite TTS | 1051±1295% interval 1039 to 1063 | 3,628 | Sept 2026 | $11.03 /1M chars |
| 25 | 25 | Simba 3.0 | 1038±1295% interval 1026 to 1050 | 3,725 | Feb 2026 | $6.58 /1M chars |
| 26 | 26-29 |  Speech 2.8 HD | 1025±1195% interval 1014 to 1036 | 4,199 | Feb 2026 | $100.00 /1M chars |
| 27 | 26-29 | Speech 2.8 Turbo | 1024±1195% interval 1013 to 1035 | 4,567 | Feb 2026 | $60.00 /1M chars |
| 28 | 26-32 |  Breeze TTS 2 | 1019±1295% interval 1007 to 1031 | 3,066 | Aug 2026 | $34.00 /1M chars |
| 29 | 26-33 | Gradium TTS (Aug 2026) | 1018±1295% interval 1006 to 1030 | 3,018 | Aug 2026 | $47.22 /1M chars |
| 30 | 28-35 | Fish Audio S2.1 Pro (Oct 2026) | 1011±1395% interval 998 to 1024 | 2,383 | Oct 2026 | $15.00 /1M chars |
| 31 | 28-35 | Fish Audio S2 Pro | 1010±1195% interval 999 to 1021 | 5,066 | Mar 2026 | $15.00 /1M chars |
| 32 | 28-35 | Voxtral TTS | 1007±1295% interval 995 to 1019 | 3,309 | Mar 2026 | $16.00 /1M chars |
| 33 | 29-35 | OpenAudio S1 Mini | 1006±1295% interval 994 to 1018 | 3,200 | Jun 2025 | $15.00 /1M chars |
| 34 | 30-35 | Multilingual v2 | 1001±1295% interval 989 to 1013 | 4,195 | Aug 2023 | $100.00 /1M chars |
| 35 | 35 | OpenAudio S1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 7,092 | Jun 2025 | $15.00 /1M chars |
| 36 | 35-38 | Flash v2.5 | 988±1295% interval 976 to 1000 | 4,193 | Dec 2024 | $50.00 /1M chars |
| 37 | 36-38 | Fish Audio S1 | 987±1295% interval 975 to 999 | 4,006 | Oct 2025 | $15.00 /1M chars |
| 38 | 36-38 | Turbo v2.5 | 984±1395% interval 971 to 997 | 3,071 | Jul 2024 | $50.00 /1M chars |
| 39 | 39-42 |  Kugel 3 | 968±1295% interval 956 to 980 | 4,406 | Jun 2026 | N/A |
| 40 | 39-42 |  Higgs Audio V3 TTS | 964±1395% interval 951 to 977 | 2,843 | Jun 2026 | $15.00 /1M chars |
| 41 | 39-42 | Sonic 3 | 963±1395% interval 950 to 976 | 3,006 | Oct 2025 | $49.00 /1M chars |
| 42 | 39-42 |  Soniox TTS Real-Time v2 | 962±1395% interval 949 to 975 | 2,577 | Aug 2026 | $14.23 /1M chars |
| 43 | 43-45 |  Chatterbox  | 943±1395% interval 930 to 956 | 2,945 | May 2025 | $25.00 /1M chars |
| 44 | 43-46 | 943±1795% interval 926 to 960 | 1,060 | Jul 2026 | N/A | |
| 45 | 43-46 |  Raon SpeechLM | 932±1395% interval 919 to 945 | 2,518 | Apr 2026 | N/A |
| 46 | 45-46 |  Noiz TTS | 927±1495% interval 913 to 941 | 2,562 | Nov 2025 | N/A |
| 47 | 47 | Lightning v3.1 | 887±1495% interval 873 to 901 | 2,629 | Mar 2026 | $25.00 /1M chars |
| 48 | 48 |  XTTS v2 | 849±1595% interval 834 to 864 | 2,746 | Nov 2023 | $40.44 /1M chars |
| 49 | 49 |  OpenVoice v2 | 824±1695% interval 808 to 840 | 2,356 | Apr 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.