Provider Voice Arena LeaderboardArtificial Analysis
Compare Text to Speech (TTS) models using each provider's own native voices.
Range | Model | Elo | Samples | Arena Voices | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|
| 1 | 1-2 |  Eleven v4 Turbo | 1329±1795% interval 1312 to 1346 | 1,839 | Sept 2026 | $40.0 /1M chars | |
| 2 | 1-2 | Eleven v4 | 1328±1795% interval 1311 to 1345 | 2,135 | Sept 2026 | $80.0 /1M chars | |
| 3 | 3-4 |  Qwen-Audio-3.1-TTS-Plus | 1296±1695% interval 1280 to 1312 | 1,750 | Sept 2026 | $19.3 /1M chars | |
| 4 | 3-5 |  Sonic 3.6 | 1287±1595% interval 1272 to 1302 | 2,564 | Aug 2026 | $49.0 /1M chars | |
| 5 | 4-6 |  Gemini 3.8 Flash TTS | 1278±1595% interval 1263 to 1293 | 2,806 | Sept 2026 | $16.5 /1M chars | |
| 6 | 5-7 | Qwen-Audio-3.0-TTS-Plus | 1265±1495% interval 1251 to 1279 | 2,264 | Sept 2026 | $19.3 /1M chars | |
| 7 | 6-8 |  Realtime TTS-2 | 1262±1595% interval 1247 to 1277 | 2,011 | Aug 2026 | $20.8 /1M chars | |
| 8 | 8-10 | Gemini 3.8 Flash-Lite TTS | 1248±1495% interval 1234 to 1262 | 2,810 | Sept 2026 | $11.0 /1M chars | |
| 9 | 8-10 |  Simba 3.2 | 1245±1395% interval 1232 to 1258 | 3,178 | Jul 2026 | $6.6 /1M chars | |
| 10 | 8-10 |  Fish Audio Drama 3 Preview  | 1244±1595% interval 1229 to 1259 | 1,999 | Oct 2026 | $15.0 /1M chars | |
| 11 | 11-16 |  Breeze TTS 2 | 1222±1495% interval 1208 to 1236 | 2,138 | Aug 2026 | $34.0 /1M chars | |
| 12 | 11-16 | Realtime TTS-2 Flash | 1219±1395% interval 1206 to 1232 | 2,459 | Aug 2026 | $10.4 /1M chars | |
| 13 | 11-16 |  Luna TTS | 1217±1295% interval 1205 to 1229 | 3,382 | Jun 2026 | $15.0 /1M chars | |
| 14 | 11-16 |  StepAudio 2.5 TTS (Aug 2026) | 1216±1495% interval 1202 to 1230 | 2,028 | Aug 2026 | $85.0 /1M chars | |
| 15 | 11-16 | Gemini 3.1 Flash TTS | 1213±1195% interval 1202 to 1224 | 4,143 | Apr 2026 | $18.3 /1M chars | |
| 16 | 11-16 | v3 Conversational | 1210±1395% interval 1197 to 1223 | 2,610 | Aug 2026 | $50.0 /1M chars | |
| 17 | 17-19 | Sonic 3.5 | 1191±1195% interval 1180 to 1202 | 3,667 | May 2026 | $49.0 /1M chars | |
| 18 | 17-20 | Fish Audio S2.1 Pro (Oct 2026) | 1190±1495% interval 1176 to 1204 | 1,929 | Oct 2026 | $15.0 /1M chars | |
| 19 | 17-23 | Eleven v3 | 1180±1195% interval 1169 to 1191 | 4,960 | Feb 2026 | $100.0 /1M chars | |
| 20 | 18-23 |  Soniox TTS Real-Time v2 | 1179±1195% interval 1168 to 1190 | 5,229 | Aug 2026 | $14.2 /1M chars | |
| 21 | 19-23 |  Gradium TTS (Sep 2026) | 1174±1495% interval 1160 to 1188 | 2,029 | Sept 2026 | $47.8 /1M chars | |
| 22 | 19-23 |  Speech 2.8 HD | 1174±1195% interval 1163 to 1185 | 5,043 | Feb 2026 | $100.0 /1M chars | |
| 23 | 19-23 |  Lightning V3.1 Pro (Jul 2026) | 1170±1395% interval 1157 to 1183 | 2,645 | Jul 2026 | $19.5 /1M chars | |
| 24 | 24-27 |  Falcon 2 | 1154±1395% interval 1141 to 1167 | 2,319 | Jul 2026 | $10.0 /1M chars | |
| 25 | 24-27 | Speech 2.8 Turbo | 1152±1195% interval 1141 to 1163 | 4,823 | Feb 2026 | $60.0 /1M chars | |
| 26 | 24-28 | Gradium TTS (Aug 2026) | 1152±1395% interval 1139 to 1165 | 2,286 | Aug 2026 | $47.2 /1M chars | |
| 27 | 24-30 |  SpaceXAI TTS | 1146±1495% interval 1132 to 1160 | 1,744 | Mar 2026 | $15.0 /1M chars | |
| 28 | 25-31 |  Async Flash v1.5 | 1141±1295% interval 1129 to 1153 | 2,550 | May 2026 | $10.1 /1M chars | |
| 29 | 27-32 |  Azure HD 2.5 | 1137±1295% interval 1125 to 1149 | 2,868 | Mar 2026 | $22.0 /1M chars | |
| 30 | 27-32 | Step TTS 2 (Mar 2026) | 1136±1295% interval 1124 to 1148 | 2,679 | Feb 2026 | $40.0 /1M chars | |
| 31 | 28-34 | Async Pro v1.0 | 1129±1295% interval 1117 to 1141 | 2,440 | May 2026 | $20.2 /1M chars | |
| 32 | 29-34 | Speech 2.6 HD | 1128±1195% interval 1117 to 1139 | 4,195 | Oct 2025 | $100.0 /1M chars | |
| 33 | 31-35 | Speech 2.6 Turbo | 1122±1195% interval 1111 to 1133 | 4,483 | Oct 2025 | $60.0 /1M chars | |
| 34 | 31-36 | Simba 3.0 | 1122±1295% interval 1110 to 1134 | 2,889 | Feb 2026 | $6.6 /1M chars | |
| 35 | 33-37 | Fish Audio S2 Pro | 1114±1295% interval 1102 to 1126 | 2,621 | Mar 2026 | $15.0 /1M chars | |
| 36 | 34-38 | Speech-02-HD | 1111±1195% interval 1100 to 1122 | 4,573 | Mar 2025 | $100.0 /1M chars | |
| 37 | 35-42 |  Chatterbox HD | 1105±1295% interval 1093 to 1117 | 2,592 | — | May 2025 | $40.0 /1M chars |
| 38 | 36-43 |  TTS-1 HD | 1102±1195% interval 1091 to 1113 | 3,709 | Nov 2023 | $30.0 /1M chars | |
| 39 | 36-45 | Step Audio EditX (Mar 2026) | 1100±1295% interval 1088 to 1112 | 2,249 | Feb 2026 | N/A | |
| 40 | 37-45 | Turbo v2.5 | 1097±1095% interval 1087 to 1107 | 6,975 | Jul 2024 | $50.0 /1M chars | |
| 41 | 37-45 | Multilingual v2 | 1096±1095% interval 1086 to 1106 | 7,429 | Aug 2023 | $100.0 /1M chars | |
| 42 | 37-46 |  Speech 2.6 | 1096±1295% interval 1084 to 1108 | 2,352 | Jul 2026 | N/A | |
| 43 | 38-47 | Speech-02-Turbo | 1091±1195% interval 1080 to 1102 | 3,927 | Mar 2025 | $60.0 /1M chars | |
| 44 | 39-48 | TTS-1 | 1090±1195% interval 1079 to 1101 | 6,237 | Nov 2023 | $15.0 /1M chars | |
| 45 | 39-50 |  Voxtral TTS | 1089±1295% interval 1077 to 1101 | 2,345 | Mar 2026 | $16.0 /1M chars | |
| 46 | 41-51 | Gemini 2.5 Flash Lite TTS | 1085±1295% interval 1073 to 1097 | 3,249 | Dec 2025 | $9.2 /1M chars | |
| 47 | 43-51 | OpenAudio S1 | 1083±1195% interval 1072 to 1094 | 4,600 | Jun 2025 | $15.0 /1M chars | |
| 48 | 44-51 | Studio | 1079±1195% interval 1068 to 1090 | 4,537 | Feb 2023 | $160.0 /1M chars | |
| 49 | 45-51 | Flash v2.5 | 1078±1195% interval 1067 to 1089 | 5,805 | Dec 2024 | $50.0 /1M chars | |
| 50 | 45-52 | GPT-Realtime-2 | 1078±1295% interval 1066 to 1090 | 2,224 | May 2026 | $191.6 /1M chars | |
| 51 | 46-57 | Journey | 1074±1395% interval 1061 to 1087 | 2,327 | Dec 2023 | $160.0 /1M chars | |
| 52 | 51-60 | T2A-01-HD | 1066±1195% interval 1055 to 1077 | 5,024 | Jan 2025 | $50.0 /1M chars | |
| 53 | 50-63 |  Maya 2 Flash | 1065±1395% interval 1052 to 1078 | 2,081 | Jul 2026 | N/A | |
| 54 | 51-62 |  Kokoro 82M v1.0 | 1064±1195% interval 1053 to 1075 | 5,386 | Jan 2025 | $0.7 /1M chars | |
| 55 | 51-62 |  Polly Generative | 1064±1295% interval 1052 to 1076 | 3,801 | May 2024 | $30.0 /1M chars | |
| 56 | 51-63 |  Magpie-Multilingual 357M (Feb 2026) | 1064±1295% interval 1052 to 1076 | 2,231 | Feb 2026 | N/A | |
| 57 | 52-63 | Chirp 3: HD | 1061±1295% interval 1049 to 1073 | 3,419 | Mar 2025 | $30.0 /1M chars | |
| 58 | 52-64 | Gemini 2.5 Flash TTS (Dec 2025) | 1060±1295% interval 1048 to 1072 | 2,926 | Dec 2025 | $9.2 /1M chars | |
| 59 | 52-66 | Sonic 3 | 1058±1295% interval 1046 to 1070 | 3,539 | Oct 2025 | $49.0 /1M chars | |
| 60 | 52-66 |  Coda | 1057±1295% interval 1045 to 1069 | 2,404 | May 2026 | $50.0 /1M chars | |
| 61 | 52-67 |  Octave 2 | 1055±1295% interval 1043 to 1067 | 3,151 | Oct 2025 | $87.5 /1M chars | |
| 62 | 52-68 |  MiMo-V2.5-TTS | 1054±1395% interval 1041 to 1067 | 2,066 | - | N/A | |
| 63 | 53-69 |  Flux TTS | 1052±1395% interval 1039 to 1065 | 2,116 | Aug 2026 | $45.0 /1M chars | |
| 64 | 58-70 | Async Flash v1.0 | 1049±1195% interval 1038 to 1060 | 4,052 | Jul 2025 | $10.1 /1M chars | |
| 65 | 59-71 | Maya 2 Global | 1047±1395% interval 1034 to 1060 | 1,937 | Jul 2026 | N/A | |
| 66 | 59-71 | Maya1 | 1046±1295% interval 1034 to 1058 | 3,301 | Jun 2025 | N/A | |
| 67 | 54-76 | OpenAudio S1 Mini | 1044±2095% interval 1024 to 1064 | 1,682 | Jun 2025 | $15.0 /1M chars | |
| 68 | 62-75 |  Higgs Audio V3 TTS | 1042±1395% interval 1029 to 1055 | 2,159 | Jun 2026 | $15.0 /1M chars | |
| 69 | 64-75 | Octave TTS | 1039±1195% interval 1028 to 1050 | 4,699 | Feb 2025 | $87.5 /1M chars | |
| 70 | 64-76 |  Bland Speech v3 | 1039±1395% interval 1026 to 1052 | 2,443 | Aug 2026 | $40.0 /1M chars | |
| 71 | 64-76 | Gemini 2.5 Pro (Dec 2025) | 1037±1395% interval 1024 to 1050 | 2,464 | Dec 2025 | $18.3 /1M chars | |
| 72 | 63-77 | Azure Neural | 1034±1995% interval 1015 to 1053 | 1,156 | Sept 2018 | $15.0 /1M chars | |
| 73 | 68-77 | MAI-Voice-1 | 1031±1295% interval 1019 to 1043 | 2,322 | Apr 2026 | N/A | |
| 74 | 69-77 | T2A-01-Turbo | 1030±1195% interval 1019 to 1041 | 4,958 | Jan 2025 | $30.0 /1M chars | |
| 75 | 68-77 | Polly Long-Form | 1030±1395% interval 1017 to 1043 | 1,960 | Nov 2023 | $100.0 /1M chars | |
| 76 | 72-77 | Chatterbox  | 1026±1195% interval 1015 to 1037 | 4,697 | May 2025 | $25.0 /1M chars | |
| 77 | 72-77 | Lightning v3.1 | 1024±1395% interval 1011 to 1037 | 2,281 | Mar 2026 | $25.0 /1M chars | |
| 78 | 78-79 |  Raon SpeechLM | 1005±1395% interval 992 to 1018 | 2,135 | Apr 2026 | N/A | |
| 79 | 79 |  Zonos-v0.1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 4,846 | Feb 2025 | $20.0 /1M chars | |
| 80 | 80 | Murf Speech Gen 2 | 986±1295% interval 974 to 998 | 4,994 | Jul 2024 | $100.0 /1M chars | |
| 81 | 81-83 | VibeVoice 1.5B | 957±1495% interval 943 to 971 | 2,127 | Aug 2025 | N/A | |
| 82 | 81-82 |  OpenVoice v2 | 957±1395% interval 944 to 970 | 3,042 | — | Apr 2024 | $8.3 /1M chars |
| 83 | 81-86 |  Neuphonic TTS | 943±1495% interval 929 to 957 | 2,421 | Oct 2024 | $20.8 /1M chars | |
| 84 | 83-86 | Qwen3 TTS Flash | 942±1495% interval 928 to 956 | 2,167 | Sept 2025 | $11.0 /1M chars | |
| 85 | 83-86 | Qwen3 TTS | 932±1395% interval 919 to 945 | 2,995 | Jan 2026 | $13.8 /1M chars | |
| 86 | 83-87 |  Kugel 3 | 931±1395% interval 918 to 944 | 4,262 | Jun 2026 | N/A | |
| 87 | 87-88 | WaveNet | 918±1295% interval 906 to 930 | 6,306 | Sept 2016 | $4.0 /1M chars | |
| 88 | 85-89 |  XTTS v2 | 917±1595% interval 902 to 932 | 2,611 | — | Nov 2023 | $40.4 /1M chars |
| 89 | 87-92 | Mist V2 | 904±1595% interval 889 to 919 | 2,954 | Mar 2025 | $31.1 /1M chars | |
| 90 | 89-93 | Polly Neural | 897±1495% interval 883 to 911 | 2,878 | Jul 2019 | $16.0 /1M chars | |
| 91 | 89-93 | Neural2 | 894±1295% interval 882 to 906 | 6,591 | Jun 2022 | $16.0 /1M chars | |
| 92 | 89-94 |  StyleTTS 2 | 892±1595% interval 877 to 907 | 2,584 | — | Jun 2023 | $2.8 /1M chars |
| 93 | 90-94 | Standard | 886±1295% interval 874 to 898 | 6,650 | Aug 2018 | $4.0 /1M chars | |
| 94 | 92-94 |  Noiz TTS | 878±1595% interval 863 to 893 | 2,269 | Nov 2025 | N/A | |
| 95 | 95-96 |  MetaVoice v1 | 848±1895% interval 830 to 866 | 1,572 | — | Feb 2024 | N/A |
| 96 | 95-96 | Polly Standard | 832±1695% interval 816 to 848 | 3,502 | Nov 2016 | $4.0 /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.
Frequently Asked Questions
The top Text to Speech models by Elo rating are: 1. Eleven v4 Turbo (Elo 1329), 2. Eleven v4 (Elo 1328), 3. Qwen-Audio-3.1-TTS-Plus (Elo 1296), 4. Sonic 3.6 (Elo 1287), and 5. Gemini 3.8 Flash TTS (Elo 1278). Rankings are based on blind user votes in the Speech Arena.
Kokoro 82M v1.0 is the most affordable at $0.65 per 1M characters with an Elo score of 1064. Other affordable options include StyleTTS 2 at $2.82 per 1M characters.
The top 5 open weights Text to Speech models are: 1. Fish Audio Drama 3 Preview (Elo 1244), 2. Breeze TTS 2 (Elo 1222), 3. Fish Audio S2 Pro (Elo 1114), 4. Step Audio EditX (Mar 2026) (Elo 1100), and 5. Voxtral TTS (Elo 1089).