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 | Pricing 1 | |
|---|---|---|---|---|---|---|---|
| 1 | 1-2 |  Eleven v4 | 1340±1595% interval 1325 to 1355 | 2,742 | Sept 2026 | $80.00 /1M chars | |
| 2 | 1-2 | Eleven v4 Turbo | 1339±1695% interval 1323 to 1355 | 2,446 | Sept 2026 | $40.00 /1M chars | |
| 3 | 3-5 |  Qwen-Audio-3.1-TTS-Plus | 1300±1495% interval 1286 to 1314 | 2,490 | Sept 2026 | $19.31 /1M chars | |
| 4 | 3-6 |  Sonic 3.6 | 1294±1395% interval 1281 to 1307 | 3,366 | Aug 2026 | $49.00 /1M chars | |
| 5 | 3-6 |  Simba 3.5 | 1294±1795% interval 1277 to 1311 | 1,732 | Nov 2026 | $6.58 /1M chars | |
| 6 | 4-8 |  Gemini 3.8 Flash TTS | 1284±1395% interval 1271 to 1297 | 3,633 | Sept 2026 | $16.49 /1M chars | |
| 7 | 6-11 |  Fish Audio Drama 3  | 1275±1795% interval 1258 to 1292 | 1,742 | Oct 2026 | $15.00 /1M chars | |
| 8 | 6-11 |  Lightning V3.1 Pro (Oct 2026) | 1273±1595% interval 1258 to 1288 | 2,064 | Oct 2026 | $19.50 /1M chars | |
| 9 | 7-11 |  Realtime TTS-2 | 1268±1395% interval 1255 to 1281 | 2,761 | Aug 2026 | $20.83 /1M chars | |
| 10 | 7-11 | Qwen-Audio-3.0-TTS-Plus | 1264±1395% interval 1251 to 1277 | 3,056 | Sept 2026 | $19.31 /1M chars | |
| 11 | 9-12 | Gemini 3.8 Flash-Lite TTS | 1260±1295% interval 1248 to 1272 | 3,640 | Sept 2026 | $11.03 /1M chars | |
| 12 | 11-12 | Simba 3.2 | 1250±1195% interval 1239 to 1261 | 3,966 | Jul 2026 | $6.58 /1M chars | |
| 13 | 12-14 | Fish Audio Drama 3 Preview | 1239±1395% interval 1226 to 1252 | 2,795 | Oct 2026 | $15.00 /1M chars | |
| 14 | 13-14 |  Breeze TTS 2 | 1229±1395% interval 1216 to 1242 | 2,937 | Aug 2026 | $34.00 /1M chars | |
| 15 | 15-20 |  StepAudio 2.5 TTS (Aug 2026) | 1215±1295% interval 1203 to 1227 | 2,814 | Aug 2026 | $85.00 /1M chars | |
| 16 | 14-20 |  AssemblyAI-TTS-1 | 1215±1595% interval 1200 to 1230 | 1,867 | Oct 2026 | $15.00 /1M chars | |
| 17 | 15-20 | Realtime TTS-2 Flash | 1215±1295% interval 1203 to 1227 | 3,235 | Aug 2026 | $10.42 /1M chars | |
| 18 | 15-20 | v3 Conversational | 1214±1295% interval 1202 to 1226 | 3,358 | Aug 2026 | $50.00 /1M chars | |
| 19 | 15-20 | Gemini 3.1 Flash TTS | 1213±1095% interval 1203 to 1223 | 4,812 | Apr 2026 | $18.31 /1M chars | |
| 20 | 15-20 |  Voxtral 3 TTS | 1213±1395% interval 1200 to 1226 | 2,258 | Oct 2026 | $13.00 /1M chars | |
| 21 | 21-23 |  Luna TTS | 1199±1195% interval 1188 to 1210 | 4,052 | Jun 2026 | $15.00 /1M chars | |
| 22 | 21-24 | Sonic 3.5 | 1195±1195% interval 1184 to 1206 | 4,319 | May 2026 | $49.00 /1M chars | |
| 23 | 21-26 | Eleven v3 | 1189±1095% interval 1179 to 1199 | 5,557 | Feb 2026 | $100.00 /1M chars | |
| 24 | 22-29 | Fish Audio S2.1 Pro (Oct 2026) | 1185±1395% interval 1172 to 1198 | 2,635 | Oct 2026 | $15.00 /1M chars | |
| 25 | 23-29 |  Ming-3.0-tts | 1182±1395% interval 1169 to 1195 | 2,640 | Oct 2026 | N/A | |
| 26 | 23-29 |  Soniox TTS Real-Time v2 | 1181±1095% interval 1171 to 1191 | 5,924 | Aug 2026 | $14.23 /1M chars | |
| 27 | 24-30 |  Gradium TTS (Sep 2026) | 1175±1295% interval 1163 to 1187 | 2,740 | Sept 2026 | $47.78 /1M chars | |
| 28 | 25-30 |  Speech 2.8 HD | 1175±1095% interval 1165 to 1185 | 5,648 | Feb 2026 | $100.00 /1M chars | |
| 29 | 21-34 |  Falcon 2.1 | 1175±2595% interval 1150 to 1200 | 236 | Oct 2026 | $10.00 /1M chars | |
| 30 | 27-32 | Gradium TTS (Oct 2026) | 1168±1395% interval 1155 to 1181 | 2,147 | Sept 2026 | $47.78 /1M chars | |
| 31 | 30-34 |  SpaceXAI TTS | 1161±1295% interval 1149 to 1173 | 2,298 | Mar 2026 | $15.00 /1M chars | |
| 32 | 30-34 | Falcon 2 | 1158±1295% interval 1146 to 1170 | 2,913 | Jul 2026 | $10.00 /1M chars | |
| 33 | 31-35 | Gradium TTS (Aug 2026) | 1153±1295% interval 1141 to 1165 | 2,965 | Aug 2026 | $47.22 /1M chars | |
| 34 | 31-35 | Speech 2.8 Turbo | 1151±1095% interval 1141 to 1161 | 5,391 | Feb 2026 | $60.00 /1M chars | |
| 35 | 33-37 |  Azure HD 2.5 | 1145±1195% interval 1134 to 1156 | 3,350 | Mar 2026 | $22.00 /1M chars | |
| 36 | 35-38 |  Async Flash v1.5 | 1138±1195% interval 1127 to 1149 | 3,082 | May 2026 | $10.10 /1M chars | |
| 37 | 35-38 | Step TTS 2 (Mar 2026) | 1136±1195% interval 1125 to 1147 | 3,137 | Feb 2026 | $40.00 /1M chars | |
| 38 | 36-40 | Async Pro v1.0 | 1128±1195% interval 1117 to 1139 | 2,931 | May 2026 | $20.20 /1M chars | |
| 39 | 38-40 | Speech 2.6 HD | 1124±1095% interval 1114 to 1134 | 4,616 | Oct 2025 | $100.00 /1M chars | |
| 40 | 38-41 | Speech 2.6 Turbo | 1123±1095% interval 1113 to 1133 | 4,850 | Oct 2025 | $60.00 /1M chars | |
| 41 | 39-47 | Simba 3.0 | 1114±1195% interval 1103 to 1125 | 3,340 | Feb 2026 | $6.58 /1M chars | |
| 42 | 39-48 | Phonon 31M (English) | 1111±1395% interval 1098 to 1124 | 1,943 | Oct 2026 | $0.00 /1M chars | |
| 43 | 40-48 |  Coda v2 | 1111±1395% interval 1098 to 1124 | 1,957 | Oct 2026 | $50.00 /1M chars | |
| 44 | 41-47 |  Chatterbox HD | 1111±1195% interval 1100 to 1122 | 2,962 | — | May 2025 | $40.00 /1M chars |
| 45 | 41-48 |  TTS-1 HD | 1108±1195% interval 1097 to 1119 | 4,052 | Nov 2023 | $30.00 /1M chars | |
| 46 | 41-50 | Speech-02-HD | 1104±1195% interval 1093 to 1115 | 4,908 | Mar 2025 | $100.00 /1M chars | |
| 47 | 41-50 | Fish Audio S2 Pro | 1104±1195% interval 1093 to 1115 | 2,999 | Mar 2026 | $15.00 /1M chars | |
| 48 | 42-54 | Step Audio EditX (Mar 2026) | 1100±1295% interval 1088 to 1112 | 2,607 | Feb 2026 | N/A | |
| 49 | 46-56 | Voxtral TTS | 1094±1195% interval 1083 to 1105 | 2,744 | Mar 2026 | $16.00 /1M chars | |
| 50 | 48-54 | Turbo v2.5 | 1094±1095% interval 1084 to 1104 | 7,281 | Jul 2024 | $50.00 /1M chars | |
| 51 | 48-56 | Multilingual v2 | 1093±1095% interval 1083 to 1103 | 7,702 | Aug 2023 | $100.00 /1M chars | |
| 52 | 48-56 |  Speech 2.6 | 1089±1295% interval 1077 to 1101 | 2,825 | Jul 2026 | N/A | |
| 53 | 48-56 | Speech-02-Turbo | 1089±1195% interval 1078 to 1100 | 4,249 | Mar 2025 | $60.00 /1M chars | |
| 54 | 48-56 | OpenAudio S1 | 1089±1195% interval 1078 to 1100 | 4,863 | Jun 2025 | $15.00 /1M chars | |
| 55 | 51-57 | TTS-1 | 1084±1095% interval 1074 to 1094 | 6,521 | Nov 2023 | $15.00 /1M chars | |
| 56 | 49-59 | Gemini 2.5 Flash Lite TTS | 1083±1195% interval 1072 to 1094 | 3,520 | Dec 2025 | $9.15 /1M chars | |
| 57 | 55-62 | Flash v2.5 | 1074±1095% interval 1064 to 1084 | 6,036 | Dec 2024 | $50.00 /1M chars | |
| 58 | 55-64 | Studio | 1073±1195% interval 1062 to 1084 | 4,801 | Feb 2023 | $160.00 /1M chars | |
| 59 | 56-64 | T2A-01-HD | 1073±1195% interval 1062 to 1084 | 5,258 | Jan 2025 | $50.00 /1M chars | |
| 60 | 55-66 | GPT-Realtime-2 | 1072±1295% interval 1060 to 1084 | 2,554 | May 2026 | $191.56 /1M chars | |
| 61 | 57-68 | Gemini 2.5 Flash TTS (Dec 2025) | 1070±1295% interval 1058 to 1082 | 3,131 | Dec 2025 | $9.15 /1M chars | |
| 62 | 57-69 | Journey | 1068±1295% interval 1056 to 1080 | 2,528 | Dec 2023 | $160.00 /1M chars | |
| 63 | 58-70 |  Polly Generative | 1063±1195% interval 1052 to 1074 | 3,994 | May 2024 | $30.00 /1M chars | |
| 64 | 58-71 |  Maya 2 Flash | 1062±1295% interval 1050 to 1074 | 2,449 | Jul 2026 | N/A | |
| 65 | 60-71 | Chirp 3: HD | 1061±1195% interval 1050 to 1072 | 3,636 | Mar 2025 | $30.00 /1M chars | |
| 66 | 61-72 |  Kokoro 82M v1.0 | 1061±1195% interval 1050 to 1072 | 5,628 | Jan 2025 | $0.65 /1M chars | |
| 67 | 61-72 |  Magpie-Multilingual 357M (Feb 2026) | 1060±1295% interval 1048 to 1072 | 2,513 | Feb 2026 | N/A | |
| 68 | 62-72 | Sonic 3 | 1059±1195% interval 1048 to 1070 | 3,754 | Oct 2025 | $49.00 /1M chars | |
| 69 | 62-75 |  Octave 2 | 1057±1295% interval 1045 to 1069 | 3,382 | Oct 2025 | $87.50 /1M chars | |
| 70 | 63-76 | Coda | 1052±1295% interval 1040 to 1064 | 2,711 | May 2026 | $50.00 /1M chars | |
| 71 | 63-76 |  Flux TTS | 1052±1295% interval 1040 to 1064 | 2,475 | Aug 2026 | $45.00 /1M chars | |
| 72 | 65-78 |  MiMo-V2.5-TTS | 1050±1295% interval 1038 to 1062 | 2,322 | - | N/A | |
| 73 | 69-79 | Async Flash v1.0 | 1047±1195% interval 1036 to 1058 | 4,246 | Jul 2025 | $10.10 /1M chars | |
| 74 | 68-80 | Maya 2 Global | 1047±1395% interval 1034 to 1060 | 2,237 | Jul 2026 | N/A | |
| 75 | 69-80 | Maya1 | 1046±1295% interval 1034 to 1058 | 3,502 | Jun 2025 | N/A | |
| 76 | 64-84 | OpenAudio S1 Mini | 1042±2095% interval 1022 to 1062 | 1,678 | Jun 2025 | $15.00 /1M chars | |
| 77 | 72-81 | Octave TTS | 1039±1195% interval 1028 to 1050 | 4,856 | Feb 2025 | $87.50 /1M chars | |
| 78 | 72-81 |  Higgs Audio V3 TTS | 1038±1295% interval 1026 to 1050 | 2,394 | Jun 2026 | $15.00 /1M chars | |
| 79 | 73-84 | Gemini 2.5 Pro (Dec 2025) | 1037±1295% interval 1025 to 1049 | 2,622 | Dec 2025 | $18.31 /1M chars | |
| 80 | 73-84 |  Bland Speech v3 | 1035±1295% interval 1023 to 1047 | 2,818 | Aug 2026 | $40.00 /1M chars | |
| 81 | 71-86 | Azure Neural | 1032±2095% interval 1012 to 1052 | 1,156 | Sept 2018 | $15.00 /1M chars | |
| 82 | 78-86 | Polly Long-Form | 1026±1395% interval 1013 to 1039 | 2,106 | Nov 2023 | $100.00 /1M chars | |
| 83 | 79-86 | MAI-Voice-1 | 1025±1295% interval 1013 to 1037 | 2,494 | Apr 2026 | N/A | |
| 84 | 80-86 | T2A-01-Turbo | 1025±1195% interval 1014 to 1036 | 5,136 | Jan 2025 | $30.00 /1M chars | |
| 85 | 81-86 | Lightning v3.1 | 1022±1295% interval 1010 to 1034 | 2,551 | Mar 2026 | $25.00 /1M chars | |
| 86 | 82-86 | Chatterbox  | 1021±1195% interval 1010 to 1032 | 4,843 | May 2025 | $25.00 /1M chars | |
| 87 | 87-88 |  Raon SpeechLM | 1002±1395% interval 989 to 1015 | 2,432 | Apr 2026 | N/A | |
| 88 | 88 |  Zonos-v0.1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 4,985 | Feb 2025 | $20.00 /1M chars | |
| 89 | 89 | Murf Speech Gen 2 | 984±1295% interval 972 to 996 | 5,135 | Jul 2024 | $100.00 /1M chars | |
| 90 | 90-91 |  OpenVoice v2 | 955±1395% interval 942 to 968 | 3,156 | — | Apr 2024 | $8.33 /1M chars |
| 91 | 90-92 | VibeVoice 1.5B | 954±1495% interval 940 to 968 | 2,226 | Aug 2025 | N/A | |
| 92 | 91-94 |  Neuphonic TTS | 941±1495% interval 927 to 955 | 2,551 | Oct 2024 | $20.79 /1M chars | |
| 93 | 92-94 | Qwen3 TTS Flash | 940±1495% interval 926 to 954 | 2,272 | Sept 2025 | $11.03 /1M chars | |
| 94 | 92-96 | Qwen3 TTS | 928±1395% interval 915 to 941 | 3,202 | Jan 2026 | $13.79 /1M chars | |
| 95 | 94-97 |  Kugel 3 | 925±1395% interval 912 to 938 | 4,583 | Jun 2026 | N/A | |
| 96 | 95-97 | WaveNet | 916±1295% interval 904 to 928 | 6,466 | Sept 2016 | $4.00 /1M chars | |
| 97 | 94-98 |  XTTS v2 | 914±1595% interval 899 to 929 | 2,753 | — | Nov 2023 | $40.44 /1M chars |
| 98 | 96-101 | Mist V2 | 903±1595% interval 888 to 918 | 3,118 | Mar 2025 | $31.13 /1M chars | |
| 99 | 98-102 | Polly Neural | 892±1495% interval 878 to 906 | 3,022 | Jul 2019 | $16.00 /1M chars | |
| 100 | 99-102 | Neural2 | 890±1295% interval 878 to 902 | 6,736 | Jun 2022 | $16.00 /1M chars | |
| 101 | 98-102 |  StyleTTS 2 | 888±1595% interval 873 to 903 | 2,753 | — | Jun 2023 | $2.82 /1M chars |
| 102 | 99-102 | Standard | 884±1395% interval 871 to 897 | 6,822 | Aug 2018 | $4.00 /1M chars | |
| 103 | 103 |  Noiz TTS | 866±1595% interval 851 to 881 | 2,529 | Nov 2025 | N/A | |
| 104 | 104-105 |  MetaVoice v1 | 846±1895% interval 828 to 864 | 1,710 | — | Feb 2024 | N/A |
| 105 | 105 | Polly Standard | 829±1695% interval 813 to 845 | 3,645 | Nov 2016 | $4.00 /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 (Elo 1340), 2. Eleven v4 Turbo (Elo 1339), 3. Qwen-Audio-3.1-TTS-Plus (Elo 1300), 4. Sonic 3.6 (Elo 1294), and 5. Simba 3.5 (Elo 1294). 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 1061. 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 (Elo 1275), 2. Fish Audio Drama 3 Preview (Elo 1239), 3. Breeze TTS 2 (Elo 1229), 4. Ming-3.0-tts (Elo 1182), and 5. Phonon 31M (English) (Elo 1111).