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 | 1338±1595% interval 1323 to 1353 | 2,722 | Sept 2026 | $80.00 /1M chars | |
| 2 | 1-2 | Eleven v4 Turbo | 1337±1695% interval 1321 to 1353 | 2,426 | Sept 2026 | $40.00 /1M chars | |
| 3 | 3-6 |  Qwen-Audio-3.1-TTS-Plus | 1297±1495% interval 1283 to 1311 | 2,473 | Sept 2026 | $19.31 /1M chars | |
| 4 | 3-5 |  Sonic 3.6 | 1296±1395% interval 1283 to 1309 | 3,326 | Aug 2026 | $49.00 /1M chars | |
| 5 | 3-6 |  Simba 3.5 | 1293±1795% interval 1276 to 1310 | 1,701 | Nov 2026 | $6.58 /1M chars | |
| 6 | 5-8 |  Gemini 3.8 Flash TTS | 1283±1395% interval 1270 to 1296 | 3,605 | Sept 2026 | $16.49 /1M chars | |
| 7 | 6-11 |  Fish Audio Drama 3  | 1274±1795% interval 1257 to 1291 | 1,713 | Oct 2026 | $15.00 /1M chars | |
| 8 | 6-11 |  Lightning V3.1 Pro (Oct 2026) | 1272±1595% interval 1257 to 1287 | 2,026 | Oct 2026 | $19.50 /1M chars | |
| 9 | 7-11 |  Realtime TTS-2 | 1266±1395% interval 1253 to 1279 | 2,730 | Aug 2026 | $20.83 /1M chars | |
| 10 | 7-11 | Qwen-Audio-3.0-TTS-Plus | 1266±1395% interval 1253 to 1279 | 3,011 | Sept 2026 | $19.31 /1M chars | |
| 11 | 9-12 | Gemini 3.8 Flash-Lite TTS | 1259±1395% interval 1246 to 1272 | 3,602 | Sept 2026 | $11.03 /1M chars | |
| 12 | 11-12 | Simba 3.2 | 1251±1295% interval 1239 to 1263 | 3,929 | Jul 2026 | $6.58 /1M chars | |
| 13 | 12-14 | Fish Audio Drama 3 Preview | 1239±1395% interval 1226 to 1252 | 2,747 | Oct 2026 | $15.00 /1M chars | |
| 14 | 13-15 |  Breeze TTS 2 | 1229±1395% interval 1216 to 1242 | 2,874 | Aug 2026 | $34.00 /1M chars | |
| 15 | 14-20 |  AssemblyAI-TTS-1 | 1222±1595% interval 1207 to 1237 | 1,809 | Oct 2026 | $15.00 /1M chars | |
| 16 | 15-20 | v3 Conversational | 1214±1295% interval 1202 to 1226 | 3,302 | Aug 2026 | $50.00 /1M chars | |
| 17 | 15-20 | Realtime TTS-2 Flash | 1213±1295% interval 1201 to 1225 | 3,173 | Aug 2026 | $10.42 /1M chars | |
| 18 | 15-21 |  Voxtral 3 TTS | 1213±1395% interval 1200 to 1226 | 2,204 | Oct 2026 | $13.00 /1M chars | |
| 19 | 15-20 | Gemini 3.1 Flash TTS | 1213±1095% interval 1203 to 1223 | 4,754 | Apr 2026 | $18.31 /1M chars | |
| 20 | 15-21 |  StepAudio 2.5 TTS (Aug 2026) | 1211±1395% interval 1198 to 1224 | 2,760 | Aug 2026 | $85.00 /1M chars | |
| 21 | 20-22 |  Luna TTS | 1201±1195% interval 1190 to 1212 | 4,006 | Jun 2026 | $15.00 /1M chars | |
| 22 | 21-25 | Sonic 3.5 | 1194±1195% interval 1183 to 1205 | 4,265 | May 2026 | $49.00 /1M chars | |
| 23 | 22-26 | Eleven v3 | 1189±1095% interval 1179 to 1199 | 5,501 | Feb 2026 | $100.00 /1M chars | |
| 24 | 22-28 |  Ming-3.0-tts | 1185±1395% interval 1172 to 1198 | 2,587 | Oct 2026 | N/A | |
| 25 | 22-28 | Fish Audio S2.1 Pro (Oct 2026) | 1184±1395% interval 1171 to 1197 | 2,572 | Oct 2026 | $15.00 /1M chars | |
| 26 | 23-28 |  Soniox TTS Real-Time v2 | 1179±1095% interval 1169 to 1189 | 5,878 | Aug 2026 | $14.23 /1M chars | |
| 27 | 25-29 |  Speech 2.8 HD | 1174±1095% interval 1164 to 1184 | 5,610 | Feb 2026 | $100.00 /1M chars | |
| 28 | 24-29 |  Gradium TTS (Sep 2026) | 1173±1295% interval 1161 to 1185 | 2,698 | Sept 2026 | $47.78 /1M chars | |
| 29 | 27-33 | Gradium TTS (Oct 2026) | 1165±1495% interval 1151 to 1179 | 2,101 | Sept 2026 | $47.78 /1M chars | |
| 30 | 29-33 |  SpaceXAI TTS | 1158±1295% interval 1146 to 1170 | 2,256 | Mar 2026 | $15.00 /1M chars | |
| 31 | 29-33 |  Falcon 2 | 1157±1295% interval 1145 to 1169 | 2,877 | Jul 2026 | $10.00 /1M chars | |
| 32 | 30-35 | Gradium TTS (Aug 2026) | 1151±1295% interval 1139 to 1163 | 2,921 | Aug 2026 | $47.22 /1M chars | |
| 33 | 30-34 | Speech 2.8 Turbo | 1151±1095% interval 1141 to 1161 | 5,360 | Feb 2026 | $60.00 /1M chars | |
| 34 | 32-36 |  Azure HD 2.5 | 1145±1195% interval 1134 to 1156 | 3,325 | Mar 2026 | $22.00 /1M chars | |
| 35 | 34-36 |  Async Flash v1.5 | 1140±1195% interval 1129 to 1151 | 3,044 | May 2026 | $10.10 /1M chars | |
| 36 | 34-37 | Step TTS 2 (Mar 2026) | 1137±1195% interval 1126 to 1148 | 3,105 | Feb 2026 | $40.00 /1M chars | |
| 37 | 36-39 | Async Pro v1.0 | 1127±1195% interval 1116 to 1138 | 2,899 | May 2026 | $20.20 /1M chars | |
| 38 | 37-39 | Speech 2.6 HD | 1125±1095% interval 1115 to 1135 | 4,593 | Oct 2025 | $100.00 /1M chars | |
| 39 | 37-42 | Speech 2.6 Turbo | 1122±1095% interval 1112 to 1132 | 4,834 | Oct 2025 | $60.00 /1M chars | |
| 40 | 38-46 | Simba 3.0 | 1114±1195% interval 1103 to 1125 | 3,317 | Feb 2026 | $6.58 /1M chars | |
| 41 | 38-47 | Phonon 31M (English) | 1113±1495% interval 1099 to 1127 | 1,908 | Oct 2026 | $0.00 /1M chars | |
| 42 | 38-46 |  Coda v2 | 1112±1395% interval 1099 to 1125 | 1,929 | Oct 2026 | $50.00 /1M chars | |
| 43 | 40-46 |  Chatterbox HD | 1110±1195% interval 1099 to 1121 | 2,937 | — | May 2025 | $40.00 /1M chars |
| 44 | 40-47 |  TTS-1 HD | 1106±1195% interval 1095 to 1117 | 4,041 | Nov 2023 | $30.00 /1M chars | |
| 45 | 40-47 | Fish Audio S2 Pro | 1106±1195% interval 1095 to 1117 | 2,977 | Mar 2026 | $15.00 /1M chars | |
| 46 | 40-47 | Speech-02-HD | 1104±1195% interval 1093 to 1115 | 4,885 | Mar 2025 | $100.00 /1M chars | |
| 47 | 43-53 | Step Audio EditX (Mar 2026) | 1099±1295% interval 1087 to 1111 | 2,585 | Feb 2026 | N/A | |
| 48 | 47-55 | Multilingual v2 | 1093±1095% interval 1083 to 1103 | 7,691 | Aug 2023 | $100.00 /1M chars | |
| 49 | 47-55 | Turbo v2.5 | 1093±1095% interval 1083 to 1103 | 7,268 | Jul 2024 | $50.00 /1M chars | |
| 50 | 47-55 |  Speech 2.6 | 1091±1295% interval 1079 to 1103 | 2,800 | Jul 2026 | N/A | |
| 51 | 47-55 | Voxtral TTS | 1091±1295% interval 1079 to 1103 | 2,719 | Mar 2026 | $16.00 /1M chars | |
| 52 | 47-55 | Speech-02-Turbo | 1089±1195% interval 1078 to 1100 | 4,234 | Mar 2025 | $60.00 /1M chars | |
| 53 | 47-55 | OpenAudio S1 | 1088±1195% interval 1077 to 1099 | 4,844 | Jun 2025 | $15.00 /1M chars | |
| 54 | 48-56 | TTS-1 | 1085±1095% interval 1075 to 1095 | 6,509 | Nov 2023 | $15.00 /1M chars | |
| 55 | 48-58 | Gemini 2.5 Flash Lite TTS | 1083±1195% interval 1072 to 1094 | 3,506 | Dec 2025 | $9.15 /1M chars | |
| 56 | 54-61 | Flash v2.5 | 1075±1095% interval 1065 to 1085 | 6,023 | Dec 2024 | $50.00 /1M chars | |
| 57 | 55-63 | T2A-01-HD | 1073±1195% interval 1062 to 1084 | 5,251 | Jan 2025 | $50.00 /1M chars | |
| 58 | 55-66 | GPT-Realtime-2 | 1072±1295% interval 1060 to 1084 | 2,539 | May 2026 | $191.56 /1M chars | |
| 59 | 56-66 | Studio | 1072±1195% interval 1061 to 1083 | 4,795 | Feb 2023 | $160.00 /1M chars | |
| 60 | 56-68 | Gemini 2.5 Flash TTS (Dec 2025) | 1069±1295% interval 1057 to 1081 | 3,117 | Dec 2025 | $9.15 /1M chars | |
| 61 | 56-68 | Journey | 1068±1295% interval 1056 to 1080 | 2,520 | Dec 2023 | $160.00 /1M chars | |
| 62 | 57-70 |  Polly Generative | 1063±1195% interval 1052 to 1074 | 3,985 | May 2024 | $30.00 /1M chars | |
| 63 | 57-71 |  Magpie-Multilingual 357M (Feb 2026) | 1062±1295% interval 1050 to 1074 | 2,497 | Feb 2026 | N/A | |
| 64 | 57-71 |  Maya 2 Flash | 1062±1295% interval 1050 to 1074 | 2,433 | Jul 2026 | N/A | |
| 65 | 59-71 | Chirp 3: HD | 1061±1195% interval 1050 to 1072 | 3,628 | Mar 2025 | $30.00 /1M chars | |
| 66 | 59-71 |  Kokoro 82M v1.0 | 1061±1195% interval 1050 to 1072 | 5,618 | Jan 2025 | $0.65 /1M chars | |
| 67 | 60-72 | Sonic 3 | 1058±1195% interval 1047 to 1069 | 3,744 | Oct 2025 | $49.00 /1M chars | |
| 68 | 60-73 |  Octave 2 | 1058±1295% interval 1046 to 1070 | 3,377 | Oct 2025 | $87.50 /1M chars | |
| 69 | 62-75 | Coda | 1054±1295% interval 1042 to 1066 | 2,693 | May 2026 | $50.00 /1M chars | |
| 70 | 62-75 |  MiMo-V2.5-TTS | 1052±1295% interval 1040 to 1064 | 2,305 | - | N/A | |
| 71 | 62-76 |  Flux TTS | 1052±1395% interval 1039 to 1065 | 2,459 | Aug 2026 | $45.00 /1M chars | |
| 72 | 67-78 | Async Flash v1.0 | 1048±1195% interval 1037 to 1059 | 4,242 | Jul 2025 | $10.10 /1M chars | |
| 73 | 67-79 | Maya1 | 1046±1295% interval 1034 to 1058 | 3,496 | Jun 2025 | N/A | |
| 74 | 68-79 | Maya 2 Global | 1045±1395% interval 1032 to 1058 | 2,225 | Jul 2026 | N/A | |
| 75 | 63-83 | OpenAudio S1 Mini | 1042±2095% interval 1022 to 1062 | 1,678 | Jun 2025 | $15.00 /1M chars | |
| 76 | 72-80 | Octave TTS | 1039±1195% interval 1028 to 1050 | 4,850 | Feb 2025 | $87.50 /1M chars | |
| 77 | 72-81 | Gemini 2.5 Pro (Dec 2025) | 1038±1295% interval 1026 to 1050 | 2,616 | Dec 2025 | $18.31 /1M chars | |
| 78 | 72-82 |  Higgs Audio V3 TTS | 1037±1295% interval 1025 to 1049 | 2,386 | Jun 2026 | $15.00 /1M chars | |
| 79 | 73-83 |  Bland Speech v3 | 1034±1295% interval 1022 to 1046 | 2,800 | Aug 2026 | $40.00 /1M chars | |
| 80 | 70-85 | Azure Neural | 1032±2095% interval 1012 to 1052 | 1,156 | Sept 2018 | $15.00 /1M chars | |
| 81 | 76-85 | MAI-Voice-1 | 1027±1295% interval 1015 to 1039 | 2,483 | Apr 2026 | N/A | |
| 82 | 79-85 | T2A-01-Turbo | 1025±1195% interval 1014 to 1036 | 5,128 | Jan 2025 | $30.00 /1M chars | |
| 83 | 78-85 | Polly Long-Form | 1025±1395% interval 1012 to 1038 | 2,100 | Nov 2023 | $100.00 /1M chars | |
| 84 | 80-85 | Lightning v3.1 | 1022±1295% interval 1010 to 1034 | 2,529 | Mar 2026 | $25.00 /1M chars | |
| 85 | 81-85 | Chatterbox  | 1021±1195% interval 1010 to 1032 | 4,838 | May 2025 | $25.00 /1M chars | |
| 86 | 86-87 |  Raon SpeechLM | 1003±1395% interval 990 to 1016 | 2,411 | Apr 2026 | N/A | |
| 87 | 87 |  Zonos-v0.1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 4,979 | Feb 2025 | $20.00 /1M chars | |
| 88 | 88 | Murf Speech Gen 2 | 984±1295% interval 972 to 996 | 5,123 | Jul 2024 | $100.00 /1M chars | |
| 89 | 89-90 |  OpenVoice v2 | 956±1395% interval 943 to 969 | 3,152 | — | Apr 2024 | $8.33 /1M chars |
| 90 | 89-90 | VibeVoice 1.5B | 954±1495% interval 940 to 968 | 2,223 | Aug 2025 | N/A | |
| 91 | 91-93 |  Neuphonic TTS | 940±1495% interval 926 to 954 | 2,545 | Oct 2024 | $20.79 /1M chars | |
| 92 | 91-94 | Qwen3 TTS Flash | 939±1495% interval 925 to 953 | 2,263 | Sept 2025 | $11.03 /1M chars | |
| 93 | 91-95 | Qwen3 TTS | 928±1395% interval 915 to 941 | 3,199 | Jan 2026 | $13.79 /1M chars | |
| 94 | 93-96 |  Kugel 3 | 925±1395% interval 912 to 938 | 4,564 | Jun 2026 | N/A | |
| 95 | 94-96 | WaveNet | 916±1295% interval 904 to 928 | 6,459 | Sept 2016 | $4.00 /1M chars | |
| 96 | 93-97 |  XTTS v2 | 915±1595% interval 900 to 930 | 2,753 | — | Nov 2023 | $40.44 /1M chars |
| 97 | 95-100 | Mist V2 | 901±1595% interval 886 to 916 | 3,112 | Mar 2025 | $31.13 /1M chars | |
| 98 | 97-101 | Polly Neural | 892±1495% interval 878 to 906 | 3,017 | Jul 2019 | $16.00 /1M chars | |
| 99 | 97-101 | Neural2 | 890±1295% interval 878 to 902 | 6,731 | Jun 2022 | $16.00 /1M chars | |
| 100 | 97-101 |  StyleTTS 2 | 888±1595% interval 873 to 903 | 2,744 | — | Jun 2023 | $2.82 /1M chars |
| 101 | 98-101 | Standard | 884±1295% interval 872 to 896 | 6,812 | Aug 2018 | $4.00 /1M chars | |
| 102 | 102 |  Noiz TTS | 866±1595% interval 851 to 881 | 2,517 | Nov 2025 | N/A | |
| 103 | 103-104 |  MetaVoice v1 | 846±1895% interval 828 to 864 | 1,705 | — | Feb 2024 | N/A |
| 104 | 104 | Polly Standard | 830±1595% interval 815 to 845 | 3,636 | 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 1338), 2. Eleven v4 Turbo (Elo 1337), 3. Qwen-Audio-3.1-TTS-Plus (Elo 1297), 4. Sonic 3.6 (Elo 1296), and 5. Simba 3.5 (Elo 1293). 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 1274), 2. Fish Audio Drama 3 Preview (Elo 1239), 3. Breeze TTS 2 (Elo 1229), 4. Ming-3.0-tts (Elo 1185), and 5. Phonon 31M (English) (Elo 1113).