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 | 1333±1695% interval 1317 to 1349 | 2,177 | Sept 2026 | $40.0 /1M chars | |
| 2 | 1-2 | Eleven v4 | 1333±1695% interval 1317 to 1349 | 2,469 | Sept 2026 | $80.0 /1M chars | |
| 3 | 3-4 |  Qwen-Audio-3.1-TTS-Plus | 1306±1595% interval 1291 to 1321 | 2,141 | Sept 2026 | $19.3 /1M chars | |
| 4 | 4-5 |  Sonic 3.6 | 1292±1495% interval 1278 to 1306 | 2,982 | Aug 2026 | $49.0 /1M chars | |
| 5 | 4-7 |  Gemini 3.8 Flash TTS | 1280±1495% interval 1266 to 1294 | 3,255 | Sept 2026 | $16.5 /1M chars | |
| 6 | 5-8 | Qwen-Audio-3.0-TTS-Plus | 1269±1395% interval 1256 to 1282 | 2,644 | Sept 2026 | $19.3 /1M chars | |
| 7 | 5-8 |  Realtime TTS-2 | 1267±1495% interval 1253 to 1281 | 2,390 | Aug 2026 | $20.8 /1M chars | |
| 8 | 6-10 | Gemini 3.8 Flash-Lite TTS | 1256±1395% interval 1243 to 1269 | 3,225 | Sept 2026 | $11.0 /1M chars | |
| 9 | 8-10 |  Simba 3.2 | 1249±1295% interval 1237 to 1261 | 3,607 | Jul 2026 | $6.6 /1M chars | |
| 10 | 8-10 |  Fish Audio Drama 3 Preview  | 1245±1495% interval 1231 to 1259 | 2,379 | Oct 2026 | $15.0 /1M chars | |
| 11 | 11-13 |  Breeze TTS 2 | 1227±1395% interval 1214 to 1240 | 2,534 | Aug 2026 | $34.0 /1M chars | |
| 12 | 11-16 |  Voxtral 3 TTS | 1221±1495% interval 1207 to 1235 | 1,881 | Oct 2026 | $13.0 /1M chars | |
| 13 | 11-16 | Realtime TTS-2 Flash | 1218±1395% interval 1205 to 1231 | 2,852 | Aug 2026 | $10.4 /1M chars | |
| 14 | 12-17 | v3 Conversational | 1213±1295% interval 1201 to 1225 | 3,001 | Aug 2026 | $50.0 /1M chars | |
| 15 | 12-17 | Gemini 3.1 Flash TTS | 1212±1195% interval 1201 to 1223 | 4,491 | Apr 2026 | $18.3 /1M chars | |
| 16 | 12-17 |  StepAudio 2.5 TTS (Aug 2026) | 1212±1395% interval 1199 to 1225 | 2,451 | Aug 2026 | $85.0 /1M chars | |
| 17 | 14-17 |  Luna TTS | 1204±1195% interval 1193 to 1215 | 3,785 | Jun 2026 | $15.0 /1M chars | |
| 18 | 18-22 | Sonic 3.5 | 1190±1195% interval 1179 to 1201 | 4,038 | May 2026 | $49.0 /1M chars | |
| 19 | 18-22 |  Ming-3.0-tts | 1189±1395% interval 1176 to 1202 | 2,350 | Oct 2026 | N/A | |
| 20 | 18-24 | Fish Audio S2.1 Pro (Oct 2026) | 1184±1395% interval 1171 to 1197 | 2,305 | Oct 2026 | $15.0 /1M chars | |
| 21 | 18-22 | Eleven v3 | 1184±1095% interval 1174 to 1194 | 5,306 | Feb 2026 | $100.0 /1M chars | |
| 22 | 18-24 |  Soniox TTS Real-Time v2 | 1180±1195% interval 1169 to 1191 | 5,619 | Aug 2026 | $14.2 /1M chars | |
| 23 | 22-25 |  Speech 2.8 HD | 1174±1095% interval 1164 to 1184 | 5,435 | Feb 2026 | $100.0 /1M chars | |
| 24 | 20-25 |  Gradium TTS (Sep 2026) | 1174±1395% interval 1161 to 1187 | 2,410 | Sept 2026 | $47.8 /1M chars | |
| 25 | 22-25 |  Lightning V3.1 Pro (Jul 2026) | 1169±1295% interval 1157 to 1181 | 3,030 | Jul 2026 | $19.5 /1M chars | |
| 26 | 26-29 |  SpaceXAI TTS | 1155±1395% interval 1142 to 1168 | 2,088 | Mar 2026 | $15.0 /1M chars | |
| 27 | 26-29 |  Falcon 2 | 1154±1295% interval 1142 to 1166 | 2,652 | Jul 2026 | $10.0 /1M chars | |
| 28 | 26-29 | Speech 2.8 Turbo | 1153±1095% interval 1143 to 1163 | 5,171 | Feb 2026 | $60.0 /1M chars | |
| 29 | 26-30 | Gradium TTS (Aug 2026) | 1151±1295% interval 1139 to 1163 | 2,663 | Aug 2026 | $47.2 /1M chars | |
| 30 | 28-32 |  Azure HD 2.5 | 1142±1195% interval 1131 to 1153 | 3,158 | Mar 2026 | $22.0 /1M chars | |
| 31 | 30-34 |  Async Flash v1.5 | 1137±1295% interval 1125 to 1149 | 2,867 | May 2026 | $10.1 /1M chars | |
| 32 | 30-34 | Step TTS 2 (Mar 2026) | 1135±1195% interval 1124 to 1146 | 2,970 | Feb 2026 | $40.0 /1M chars | |
| 33 | 31-36 | Async Pro v1.0 | 1127±1295% interval 1115 to 1139 | 2,726 | May 2026 | $20.2 /1M chars | |
| 34 | 32-36 | Speech 2.6 HD | 1126±1195% interval 1115 to 1137 | 4,449 | Oct 2025 | $100.0 /1M chars | |
| 35 | 33-37 | Speech 2.6 Turbo | 1120±1195% interval 1109 to 1131 | 4,701 | Oct 2025 | $60.0 /1M chars | |
| 36 | 34-40 | Simba 3.0 | 1116±1195% interval 1105 to 1127 | 3,183 | Feb 2026 | $6.6 /1M chars | |
| 37 | 35-41 |  Chatterbox HD | 1111±1295% interval 1099 to 1123 | 2,778 | — | May 2025 | $40.0 /1M chars |
| 38 | 36-41 | Speech-02-HD | 1108±1195% interval 1097 to 1119 | 4,771 | Mar 2025 | $100.0 /1M chars | |
| 39 | 36-41 | Fish Audio S2 Pro | 1108±1295% interval 1096 to 1120 | 2,832 | Mar 2026 | $15.0 /1M chars | |
| 40 | 36-41 |  TTS-1 HD | 1106±1195% interval 1095 to 1117 | 3,884 | Nov 2023 | $30.0 /1M chars | |
| 41 | 37-47 | Step Audio EditX (Mar 2026) | 1099±1295% interval 1087 to 1111 | 2,463 | Feb 2026 | N/A | |
| 42 | 41-49 | Turbo v2.5 | 1093±1095% interval 1083 to 1103 | 7,142 | Jul 2024 | $50.0 /1M chars | |
| 43 | 41-49 | Multilingual v2 | 1093±1095% interval 1083 to 1103 | 7,587 | Aug 2023 | $100.0 /1M chars | |
| 44 | 41-49 |  Speech 2.6 | 1093±1295% interval 1081 to 1105 | 2,609 | Jul 2026 | N/A | |
| 45 | 41-49 | Speech-02-Turbo | 1089±1195% interval 1078 to 1100 | 4,091 | Mar 2025 | $60.0 /1M chars | |
| 46 | 42-49 | TTS-1 | 1088±1095% interval 1078 to 1098 | 6,378 | Nov 2023 | $15.0 /1M chars | |
| 47 | 41-49 | Voxtral TTS | 1088±1295% interval 1076 to 1100 | 2,552 | Mar 2026 | $16.0 /1M chars | |
| 48 | 42-49 | Gemini 2.5 Flash Lite TTS | 1087±1195% interval 1076 to 1098 | 3,395 | Dec 2025 | $9.2 /1M chars | |
| 49 | 42-52 | OpenAudio S1 | 1084±1195% interval 1073 to 1095 | 4,734 | Jun 2025 | $15.0 /1M chars | |
| 50 | 49-57 | Flash v2.5 | 1076±1195% interval 1065 to 1087 | 5,905 | Dec 2024 | $50.0 /1M chars | |
| 51 | 49-59 | Journey | 1074±1295% interval 1062 to 1086 | 2,419 | Dec 2023 | $160.0 /1M chars | |
| 52 | 49-59 | GPT-Realtime-2 | 1073±1295% interval 1061 to 1085 | 2,403 | May 2026 | $191.6 /1M chars | |
| 53 | 50-60 | Studio | 1072±1195% interval 1061 to 1083 | 4,669 | Feb 2023 | $160.0 /1M chars | |
| 54 | 50-60 | T2A-01-HD | 1067±1195% interval 1056 to 1078 | 5,138 | Jan 2025 | $50.0 /1M chars | |
| 55 | 50-61 | Gemini 2.5 Flash TTS (Dec 2025) | 1067±1295% interval 1055 to 1079 | 3,012 | Dec 2025 | $9.2 /1M chars | |
| 56 | 50-64 |  Maya 2 Flash | 1065±1395% interval 1052 to 1078 | 2,246 | Jul 2026 | N/A | |
| 57 | 50-64 |  Magpie-Multilingual 357M (Feb 2026) | 1065±1295% interval 1053 to 1077 | 2,370 | Feb 2026 | N/A | |
| 58 | 52-64 |  Kokoro 82M v1.0 | 1063±1195% interval 1052 to 1074 | 5,495 | Jan 2025 | $0.7 /1M chars | |
| 59 | 52-65 |  Polly Generative | 1063±1195% interval 1052 to 1074 | 3,891 | May 2024 | $30.0 /1M chars | |
| 60 | 53-65 | Chirp 3: HD | 1061±1295% interval 1049 to 1073 | 3,504 | Mar 2025 | $30.0 /1M chars | |
| 61 | 54-69 |  Octave 2 | 1056±1295% interval 1044 to 1068 | 3,257 | Oct 2025 | $87.5 /1M chars | |
| 62 | 56-69 | Sonic 3 | 1054±1195% interval 1043 to 1065 | 3,629 | Oct 2025 | $49.0 /1M chars | |
| 63 | 56-70 |  Coda | 1054±1295% interval 1042 to 1066 | 2,545 | May 2026 | $50.0 /1M chars | |
| 64 | 56-70 |  MiMo-V2.5-TTS | 1054±1295% interval 1042 to 1066 | 2,209 | - | N/A | |
| 65 | 57-71 |  Flux TTS | 1052±1395% interval 1039 to 1065 | 2,275 | Aug 2026 | $45.0 /1M chars | |
| 66 | 61-71 | Async Flash v1.0 | 1049±1195% interval 1038 to 1060 | 4,140 | Jul 2025 | $10.1 /1M chars | |
| 67 | 61-72 | Maya1 | 1048±1295% interval 1036 to 1060 | 3,378 | Jun 2025 | N/A | |
| 68 | 61-72 | Maya 2 Global | 1047±1395% interval 1034 to 1060 | 2,080 | Jul 2026 | N/A | |
| 69 | 61-74 |  Higgs Audio V3 TTS | 1045±1395% interval 1032 to 1058 | 2,282 | Jun 2026 | $15.0 /1M chars | |
| 70 | 60-78 | OpenAudio S1 Mini | 1043±2095% interval 1023 to 1063 | 1,682 | Jun 2025 | $15.0 /1M chars | |
| 71 | 65-76 | Gemini 2.5 Pro (Dec 2025) | 1040±1295% interval 1028 to 1052 | 2,527 | Dec 2025 | $18.3 /1M chars | |
| 72 | 68-77 | Octave TTS | 1036±1195% interval 1025 to 1047 | 4,761 | Feb 2025 | $87.5 /1M chars | |
| 73 | 69-78 |  Bland Speech v3 | 1033±1295% interval 1021 to 1045 | 2,590 | Aug 2026 | $40.0 /1M chars | |
| 74 | 65-79 | Azure Neural | 1032±2095% interval 1012 to 1052 | 1,156 | Sept 2018 | $15.0 /1M chars | |
| 75 | 71-79 | MAI-Voice-1 | 1030±1295% interval 1018 to 1042 | 2,397 | Apr 2026 | N/A | |
| 76 | 71-79 | Polly Long-Form | 1029±1395% interval 1016 to 1042 | 2,012 | Nov 2023 | $100.0 /1M chars | |
| 77 | 72-79 | T2A-01-Turbo | 1027±1195% interval 1016 to 1038 | 5,039 | Jan 2025 | $30.0 /1M chars | |
| 78 | 73-79 | Chatterbox  | 1023±1195% interval 1012 to 1034 | 4,749 | May 2025 | $25.0 /1M chars | |
| 79 | 75-79 | Lightning v3.1 | 1020±1295% interval 1008 to 1032 | 2,405 | Mar 2026 | $25.0 /1M chars | |
| 80 | 80-81 |  Raon SpeechLM | 1004±1395% interval 991 to 1017 | 2,253 | Apr 2026 | N/A | |
| 81 | 81 |  Zonos-v0.1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 4,903 | Feb 2025 | $20.0 /1M chars | |
| 82 | 82 | Murf Speech Gen 2 | 983±1295% interval 971 to 995 | 5,046 | Jul 2024 | $100.0 /1M chars | |
| 83 | 83-84 |  OpenVoice v2 | 956±1395% interval 943 to 969 | 3,095 | — | Apr 2024 | $8.3 /1M chars |
| 84 | 83-84 | VibeVoice 1.5B | 954±1495% interval 940 to 968 | 2,172 | Aug 2025 | N/A | |
| 85 | 85-87 |  Neuphonic TTS | 940±1495% interval 926 to 954 | 2,499 | Oct 2024 | $20.8 /1M chars | |
| 86 | 85-87 | Qwen3 TTS Flash | 939±1495% interval 925 to 953 | 2,224 | Sept 2025 | $11.0 /1M chars | |
| 87 | 85-89 | Qwen3 TTS | 929±1395% interval 916 to 942 | 3,153 | Jan 2026 | $13.8 /1M chars | |
| 88 | 87-90 |  Kugel 3 | 924±1395% interval 911 to 937 | 4,425 | Jun 2026 | N/A | |
| 89 | 88-90 | WaveNet | 917±1295% interval 905 to 929 | 6,407 | Sept 2016 | $4.0 /1M chars | |
| 90 | 88-91 |  XTTS v2 | 913±1595% interval 898 to 928 | 2,713 | — | Nov 2023 | $40.4 /1M chars |
| 91 | 89-94 | Mist V2 | 902±1595% interval 887 to 917 | 3,060 | Mar 2025 | $31.1 /1M chars | |
| 92 | 91-95 | Polly Neural | 894±1495% interval 880 to 908 | 2,986 | Jul 2019 | $16.0 /1M chars | |
| 93 | 91-95 | Neural2 | 893±1295% interval 881 to 905 | 6,692 | Jun 2022 | $16.0 /1M chars | |
| 94 | 91-95 |  StyleTTS 2 | 889±1595% interval 874 to 904 | 2,682 | — | Jun 2023 | $2.8 /1M chars |
| 95 | 92-95 | Standard | 886±1395% interval 873 to 899 | 6,771 | Aug 2018 | $4.0 /1M chars | |
| 96 | 96 |  Noiz TTS | 868±1595% interval 853 to 883 | 2,455 | Nov 2025 | N/A | |
| 97 | 97-98 |  MetaVoice v1 | 845±1895% interval 827 to 863 | 1,665 | — | Feb 2024 | N/A |
| 98 | 97-98 | Polly Standard | 829±1695% interval 813 to 845 | 3,590 | 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 1333), 2. Eleven v4 (Elo 1333), 3. Qwen-Audio-3.1-TTS-Plus (Elo 1306), 4. Sonic 3.6 (Elo 1292), and 5. Gemini 3.8 Flash TTS (Elo 1280). 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 1063. 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 1245), 2. Breeze TTS 2 (Elo 1227), 3. Ming-3.0-tts (Elo 1189), 4. Fish Audio S2 Pro (Elo 1108), and 5. Step Audio EditX (Mar 2026) (Elo 1099).