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 | 1335±1795% interval 1318 to 1352 | 2,045 | Sept 2026 | $40.0 /1M chars | |
| 2 | 1-2 | Eleven v4 | 1329±1695% interval 1313 to 1345 | 2,346 | Sept 2026 | $80.0 /1M chars | |
| 3 | 3-4 |  Qwen-Audio-3.1-TTS-Plus | 1301±1695% interval 1285 to 1317 | 1,977 | Sept 2026 | $19.3 /1M chars | |
| 4 | 3-5 |  Sonic 3.6 | 1289±1495% interval 1275 to 1303 | 2,789 | Aug 2026 | $49.0 /1M chars | |
| 5 | 4-7 |  Gemini 3.8 Flash TTS | 1278±1495% interval 1264 to 1292 | 3,033 | Sept 2026 | $16.5 /1M chars | |
| 6 | 5-7 |  Realtime TTS-2 | 1267±1595% interval 1252 to 1282 | 2,205 | Aug 2026 | $20.8 /1M chars | |
| 7 | 5-8 | Qwen-Audio-3.0-TTS-Plus | 1265±1495% interval 1251 to 1279 | 2,455 | Sept 2026 | $19.3 /1M chars | |
| 8 | 8-10 | Gemini 3.8 Flash-Lite TTS | 1251±1395% interval 1238 to 1264 | 3,025 | Sept 2026 | $11.0 /1M chars | |
| 9 | 8-10 |  Fish Audio Drama 3 Preview  | 1248±1595% interval 1233 to 1263 | 2,181 | Oct 2026 | $15.0 /1M chars | |
| 10 | 8-10 |  Simba 3.2 | 1245±1295% interval 1233 to 1257 | 3,367 | Jul 2026 | $6.6 /1M chars | |
| 11 | 11-16 |  Breeze TTS 2 | 1225±1495% interval 1211 to 1239 | 2,317 | Aug 2026 | $34.0 /1M chars | |
| 12 | 11-17 |  Voxtral 3 TTS | 1218±1595% interval 1203 to 1233 | 1,651 | Oct 2026 | $13.0 /1M chars | |
| 13 | 11-17 | Realtime TTS-2 Flash | 1218±1395% interval 1205 to 1231 | 2,613 | Aug 2026 | $10.4 /1M chars | |
| 14 | 11-17 |  StepAudio 2.5 TTS (Aug 2026) | 1216±1495% interval 1202 to 1230 | 2,198 | Aug 2026 | $85.0 /1M chars | |
| 15 | 11-17 | v3 Conversational | 1214±1395% interval 1201 to 1227 | 2,788 | Aug 2026 | $50.0 /1M chars | |
| 16 | 12-17 | Gemini 3.1 Flash TTS | 1213±1195% interval 1202 to 1224 | 4,276 | Apr 2026 | $18.3 /1M chars | |
| 17 | 12-17 |  Luna TTS | 1210±1295% interval 1198 to 1222 | 3,554 | Jun 2026 | $15.0 /1M chars | |
| 18 | 18-22 | Sonic 3.5 | 1191±1195% interval 1180 to 1202 | 3,812 | May 2026 | $49.0 /1M chars | |
| 19 | 18-23 |  Ming-3.0-tts | 1190±1495% interval 1176 to 1204 | 2,104 | Oct 2026 | N/A | |
| 20 | 18-23 | Fish Audio S2.1 Pro (Oct 2026) | 1189±1495% interval 1175 to 1203 | 2,065 | Oct 2026 | $15.0 /1M chars | |
| 21 | 18-24 | Eleven v3 | 1183±1195% interval 1172 to 1194 | 5,085 | Feb 2026 | $100.0 /1M chars | |
| 22 | 18-25 |  Soniox TTS Real-Time v2 | 1180±1195% interval 1169 to 1191 | 5,367 | Aug 2026 | $14.2 /1M chars | |
| 23 | 20-25 |  Gradium TTS (Sep 2026) | 1176±1395% interval 1163 to 1189 | 2,169 | Sept 2026 | $47.8 /1M chars | |
| 24 | 21-25 |  Speech 2.8 HD | 1174±1095% interval 1164 to 1184 | 5,194 | Feb 2026 | $100.0 /1M chars | |
| 25 | 22-25 |  Lightning V3.1 Pro (Jul 2026) | 1169±1295% interval 1157 to 1181 | 2,787 | Jul 2026 | $19.5 /1M chars | |
| 26 | 26-29 | Speech 2.8 Turbo | 1155±1095% interval 1145 to 1165 | 4,966 | Feb 2026 | $60.0 /1M chars | |
| 27 | 26-30 | Gradium TTS (Aug 2026) | 1155±1395% interval 1142 to 1168 | 2,422 | Aug 2026 | $47.2 /1M chars | |
| 28 | 26-30 |  Falcon 2 | 1153±1395% interval 1140 to 1166 | 2,441 | Jul 2026 | $10.0 /1M chars | |
| 29 | 26-32 |  SpaceXAI TTS | 1150±1395% interval 1137 to 1163 | 1,875 | Mar 2026 | $15.0 /1M chars | |
| 30 | 29-33 |  Azure HD 2.5 | 1142±1195% interval 1131 to 1153 | 2,976 | Mar 2026 | $22.0 /1M chars | |
| 31 | 29-33 |  Async Flash v1.5 | 1140±1295% interval 1128 to 1152 | 2,669 | May 2026 | $10.1 /1M chars | |
| 32 | 30-34 | Step TTS 2 (Mar 2026) | 1137±1295% interval 1125 to 1149 | 2,777 | Feb 2026 | $40.0 /1M chars | |
| 33 | 30-35 | Speech 2.6 HD | 1131±1195% interval 1120 to 1142 | 4,277 | Oct 2025 | $100.0 /1M chars | |
| 34 | 32-36 | Async Pro v1.0 | 1127±1295% interval 1115 to 1139 | 2,543 | May 2026 | $20.2 /1M chars | |
| 35 | 33-38 | Simba 3.0 | 1121±1195% interval 1110 to 1132 | 2,997 | Feb 2026 | $6.6 /1M chars | |
| 36 | 33-38 | Speech 2.6 Turbo | 1120±1195% interval 1109 to 1131 | 4,554 | Oct 2025 | $60.0 /1M chars | |
| 37 | 35-40 | Fish Audio S2 Pro | 1112±1295% interval 1100 to 1124 | 2,699 | Mar 2026 | $15.0 /1M chars | |
| 38 | 35-40 | Speech-02-HD | 1111±1195% interval 1100 to 1122 | 4,636 | Mar 2025 | $100.0 /1M chars | |
| 39 | 36-42 |  Chatterbox HD | 1109±1295% interval 1097 to 1121 | 2,654 | — | May 2025 | $40.0 /1M chars |
| 40 | 37-44 |  TTS-1 HD | 1103±1195% interval 1092 to 1114 | 3,755 | Nov 2023 | $30.0 /1M chars | |
| 41 | 38-47 | Step Audio EditX (Mar 2026) | 1099±1295% interval 1087 to 1111 | 2,313 | Feb 2026 | N/A | |
| 42 | 40-47 | Turbo v2.5 | 1098±1095% interval 1088 to 1108 | 7,028 | Jul 2024 | $50.0 /1M chars | |
| 43 | 40-48 | Multilingual v2 | 1096±1095% interval 1086 to 1106 | 7,485 | Aug 2023 | $100.0 /1M chars | |
| 44 | 40-49 |  Speech 2.6 | 1096±1295% interval 1084 to 1108 | 2,434 | Jul 2026 | N/A | |
| 45 | 40-49 | Voxtral TTS | 1091±1295% interval 1079 to 1103 | 2,412 | Mar 2026 | $16.0 /1M chars | |
| 46 | 41-49 | Speech-02-Turbo | 1091±1195% interval 1080 to 1102 | 3,971 | Mar 2025 | $60.0 /1M chars | |
| 47 | 41-49 | TTS-1 | 1090±1095% interval 1080 to 1100 | 6,284 | Nov 2023 | $15.0 /1M chars | |
| 48 | 43-52 | OpenAudio S1 | 1086±1195% interval 1075 to 1097 | 4,634 | Jun 2025 | $15.0 /1M chars | |
| 49 | 43-53 | Gemini 2.5 Flash Lite TTS | 1086±1195% interval 1075 to 1097 | 3,291 | Dec 2025 | $9.2 /1M chars | |
| 50 | 48-56 | Flash v2.5 | 1077±1195% interval 1066 to 1088 | 5,832 | Dec 2024 | $50.0 /1M chars | |
| 51 | 48-56 | Studio | 1077±1195% interval 1066 to 1088 | 4,579 | Feb 2023 | $160.0 /1M chars | |
| 52 | 48-57 | Journey | 1076±1295% interval 1064 to 1088 | 2,346 | Dec 2023 | $160.0 /1M chars | |
| 53 | 48-58 | GPT-Realtime-2 | 1075±1295% interval 1063 to 1087 | 2,288 | May 2026 | $191.6 /1M chars | |
| 54 | 50-63 |  Maya 2 Flash | 1068±1395% interval 1055 to 1081 | 2,129 | Jul 2026 | N/A | |
| 55 | 50-61 | T2A-01-HD | 1067±1195% interval 1056 to 1078 | 5,056 | Jan 2025 | $50.0 /1M chars | |
| 56 | 50-62 |  Polly Generative | 1066±1195% interval 1055 to 1077 | 3,830 | May 2024 | $30.0 /1M chars | |
| 57 | 52-63 |  Kokoro 82M v1.0 | 1065±1195% interval 1054 to 1076 | 5,427 | Jan 2025 | $0.7 /1M chars | |
| 58 | 53-65 |  Magpie-Multilingual 357M (Feb 2026) | 1063±1295% interval 1051 to 1075 | 2,277 | Feb 2026 | N/A | |
| 59 | 54-65 | Gemini 2.5 Flash TTS (Dec 2025) | 1063±1295% interval 1051 to 1075 | 2,951 | Dec 2025 | $9.2 /1M chars | |
| 60 | 54-66 | Chirp 3: HD | 1061±1295% interval 1049 to 1073 | 3,446 | Mar 2025 | $30.0 /1M chars | |
| 61 | 54-68 | Sonic 3 | 1057±1295% interval 1045 to 1069 | 3,559 | Oct 2025 | $49.0 /1M chars | |
| 62 | 55-70 |  Coda | 1056±1295% interval 1044 to 1068 | 2,437 | May 2026 | $50.0 /1M chars | |
| 63 | 55-70 |  Octave 2 | 1055±1295% interval 1043 to 1067 | 3,180 | Oct 2025 | $87.5 /1M chars | |
| 64 | 57-70 |  MiMo-V2.5-TTS | 1054±1295% interval 1042 to 1066 | 2,113 | - | N/A | |
| 65 | 57-70 |  Flux TTS | 1052±1395% interval 1039 to 1065 | 2,173 | Aug 2026 | $45.0 /1M chars | |
| 66 | 61-70 | Async Flash v1.0 | 1050±1195% interval 1039 to 1061 | 4,074 | Jul 2025 | $10.1 /1M chars | |
| 67 | 61-73 | Maya 2 Global | 1048±1395% interval 1035 to 1061 | 1,975 | Jul 2026 | N/A | |
| 68 | 61-73 | Maya1 | 1047±1295% interval 1035 to 1059 | 3,315 | Jun 2025 | N/A | |
| 69 | 58-77 | OpenAudio S1 Mini | 1044±2095% interval 1024 to 1064 | 1,682 | Jun 2025 | $15.0 /1M chars | |
| 70 | 61-74 |  Higgs Audio V3 TTS | 1044±1395% interval 1031 to 1057 | 2,191 | Jun 2026 | $15.0 /1M chars | |
| 71 | 67-77 | Octave TTS | 1038±1195% interval 1027 to 1049 | 4,716 | Feb 2025 | $87.5 /1M chars | |
| 72 | 66-77 | Gemini 2.5 Pro (Dec 2025) | 1038±1295% interval 1026 to 1050 | 2,477 | Dec 2025 | $18.3 /1M chars | |
| 73 | 67-77 |  Bland Speech v3 | 1037±1295% interval 1025 to 1049 | 2,489 | Aug 2026 | $40.0 /1M chars | |
| 74 | 65-79 | Azure Neural | 1034±2095% interval 1014 to 1054 | 1,156 | Sept 2018 | $15.0 /1M chars | |
| 75 | 71-79 | T2A-01-Turbo | 1031±1195% interval 1020 to 1042 | 4,974 | Jan 2025 | $30.0 /1M chars | |
| 76 | 71-79 | MAI-Voice-1 | 1030±1295% interval 1018 to 1042 | 2,344 | Apr 2026 | N/A | |
| 77 | 71-79 | Polly Long-Form | 1029±1395% interval 1016 to 1042 | 1,973 | Nov 2023 | $100.0 /1M chars | |
| 78 | 74-79 | Chatterbox  | 1024±1195% interval 1013 to 1035 | 4,707 | May 2025 | $25.0 /1M chars | |
| 79 | 74-79 | Lightning v3.1 | 1022±1295% interval 1010 to 1034 | 2,315 | Mar 2026 | $25.0 /1M chars | |
| 80 | 80-81 |  Raon SpeechLM | 1005±1395% interval 992 to 1018 | 2,167 | Apr 2026 | N/A | |
| 81 | 81 |  Zonos-v0.1 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 4,853 | Feb 2025 | $20.0 /1M chars | |
| 82 | 82 | Murf Speech Gen 2 | 986±1295% interval 974 to 998 | 5,004 | Jul 2024 | $100.0 /1M chars | |
| 83 | 83-86 | VibeVoice 1.5B | 956±1495% interval 942 to 970 | 2,132 | Aug 2025 | N/A | |
| 84 | 83-85 |  OpenVoice v2 | 956±1395% interval 943 to 969 | 3,044 | — | Apr 2024 | $8.3 /1M chars |
| 85 | 83-87 |  Neuphonic TTS | 944±1495% interval 930 to 958 | 2,428 | Oct 2024 | $20.8 /1M chars | |
| 86 | 83-88 | Qwen3 TTS Flash | 943±1495% interval 929 to 957 | 2,172 | Sept 2025 | $11.0 /1M chars | |
| 87 | 86-89 | Qwen3 TTS | 930±1395% interval 917 to 943 | 3,018 | Jan 2026 | $13.8 /1M chars | |
| 88 | 87-89 |  Kugel 3 | 929±1395% interval 916 to 942 | 4,292 | Jun 2026 | N/A | |
| 89 | 88-90 | WaveNet | 918±1295% interval 906 to 930 | 6,315 | Sept 2016 | $4.0 /1M chars | |
| 90 | 87-91 |  XTTS v2 | 916±1595% interval 901 to 931 | 2,616 | — | Nov 2023 | $40.4 /1M chars |
| 91 | 89-94 | Mist V2 | 904±1595% interval 889 to 919 | 2,963 | Mar 2025 | $31.1 /1M chars | |
| 92 | 91-95 | Polly Neural | 897±1495% interval 883 to 911 | 2,886 | Jul 2019 | $16.0 /1M chars | |
| 93 | 91-95 | Neural2 | 894±1295% interval 882 to 906 | 6,598 | Jun 2022 | $16.0 /1M chars | |
| 94 | 91-95 |  StyleTTS 2 | 892±1595% interval 877 to 907 | 2,590 | — | Jun 2023 | $2.8 /1M chars |
| 95 | 92-96 | Standard | 886±1395% interval 873 to 899 | 6,652 | Aug 2018 | $4.0 /1M chars | |
| 96 | 95-96 |  Noiz TTS | 876±1595% interval 861 to 891 | 2,293 | Nov 2025 | N/A | |
| 97 | 97-98 |  MetaVoice v1 | 848±1895% interval 830 to 866 | 1,575 | — | Feb 2024 | N/A |
| 98 | 98 | Polly Standard | 831±1695% interval 815 to 847 | 3,508 | 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 1335), 2. Eleven v4 (Elo 1329), 3. Qwen-Audio-3.1-TTS-Plus (Elo 1301), 4. Sonic 3.6 (Elo 1289), 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 1065. 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 1248), 2. Breeze TTS 2 (Elo 1225), 3. Ming-3.0-tts (Elo 1190), 4. Fish Audio S2 Pro (Elo 1112), and 5. Step Audio EditX (Mar 2026) (Elo 1099).