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 Turbo | 1340±1595% interval 1325 to 1355 | 2,668 | Sept 2026 | $40.00 /1M chars | |
| 2 | 1-2 | Eleven v4 | 1340±1495% interval 1326 to 1354 | 2,957 | Sept 2026 | $80.00 /1M chars | |
| 3 | 3-6 | StepAudio 3 TTS | 1307±1795% interval 1290 to 1324 | 1,882 | Nov 2026 | $14.00 /1M chars | |
| 4 | 3-6 | Qwen-Audio-3.1-TTS-Plus | 1298±1495% interval 1284 to 1312 | 2,744 | Sept 2026 | $19.31 /1M chars | |
| 5 | 3-7 | Sonic 3.6 | 1294±1395% interval 1281 to 1307 | 3,643 | Aug 2026 | $49.00 /1M chars | |
| 6 | 3-8 | Simba 3.5 | 1293±1695% interval 1277 to 1309 | 1,992 | Nov 2026 | $6.58 /1M chars | |
| 7 | 5-10 | Gemini 3.8 Flash TTS | 1282±1395% interval 1269 to 1295 | 3,916 | Sept 2026 | $16.49 /1M chars | |
| 8 | 6-11 | 1277±1695% interval 1261 to 1293 | 1,996 | Oct 2026 | $15.00 /1M chars | ||
| 9 | 7-11 | Lightning V3.1 Pro (Oct 2026) | 1276±1495% interval 1262 to 1290 | 2,319 | Oct 2026 | $19.50 /1M chars | |
| 10 | 7-12 | Realtime TTS-2 | 1269±1395% interval 1256 to 1282 | 3,040 | Aug 2026 | $20.83 /1M chars | |
| 11 | 10-13 | Qwen-Audio-3.0-TTS-Plus | 1262±1295% interval 1250 to 1274 | 3,313 | Sept 2026 | $19.31 /1M chars | |
| 12 | 10-13 | Gemini 3.8 Flash-Lite TTS | 1261±1295% interval 1249 to 1273 | 3,875 | Sept 2026 | $11.03 /1M chars | |
| 13 | 12-13 | Simba 3.2 | 1251±1195% interval 1240 to 1262 | 4,164 | Jul 2026 | $6.58 /1M chars | |
| 14 | 14-15 | 1237±1395% interval 1224 to 1250 | 3,001 | Oct 2026 | $15.00 /1M chars | ||
| 15 | 14-15 | 1228±1295% interval 1216 to 1240 | 3,145 | Aug 2026 | $34.00 /1M chars | ||
| 16 | 16-21 | v3 Conversational | 1215±1295% interval 1203 to 1227 | 3,587 | Aug 2026 | $50.00 /1M chars | |
| 17 | 16-21 | StepAudio 2.5 TTS (Aug 2026) | 1214±1295% interval 1202 to 1226 | 3,024 | Aug 2026 | $85.00 /1M chars | |
| 18 | 16-21 | Gemini 3.1 Flash TTS | 1214±1095% interval 1204 to 1224 | 4,991 | Apr 2026 | $18.31 /1M chars | |
| 19 | 16-21 | Realtime TTS-2 Flash | 1213±1295% interval 1201 to 1225 | 3,471 | Aug 2026 | $10.42 /1M chars | |
| 20 | 16-21 | AssemblyAI-TTS-1 | 1212±1495% interval 1198 to 1226 | 2,098 | Oct 2026 | $15.00 /1M chars | |
| 21 | 16-21 | Voxtral 3 TTS | 1211±1395% interval 1198 to 1224 | 2,478 | Oct 2026 | $13.00 /1M chars | |
| 22 | 22-24 | Sonic 3.5 | 1195±1095% interval 1185 to 1205 | 4,494 | May 2026 | $49.00 /1M chars | |
| 23 | 22-24 | Luna TTS | 1192±1195% interval 1181 to 1203 | 4,230 | Jun 2026 | $15.00 /1M chars | |
| 24 | 22-24 | Eleven v3 | 1191±1095% interval 1181 to 1201 | 5,710 | Feb 2026 | $100.00 /1M chars | |
| 25 | 23-30 | Fish Audio S2.1 Pro (Oct 2026) | 1181±1295% interval 1169 to 1193 | 2,819 | Oct 2026 | $15.00 /1M chars | |
| 26 | 25-30 | Soniox TTS Real-Time v2 | 1179±1095% interval 1169 to 1189 | 6,102 | Aug 2026 | $14.23 /1M chars | |
| 27 | 25-30 | 1179±1295% interval 1167 to 1191 | 2,802 | Oct 2026 | N/A | ||
| 28 | 25-30 | Speech 2.8 HD | 1173±1095% interval 1163 to 1183 | 5,797 | Feb 2026 | $100.00 /1M chars | |
| 29 | 25-31 | Gradium TTS (Sep 2026) | 1172±1295% interval 1160 to 1184 | 2,934 | Sept 2026 | $47.78 /1M chars | |
| 30 | 25-31 | Gradium TTS (Oct 2026) | 1172±1395% interval 1159 to 1185 | 2,332 | Sept 2026 | $47.78 /1M chars | |
| 31 | 29-36 | SpaceXAI TTS | 1160±1295% interval 1148 to 1172 | 2,436 | Mar 2026 | $15.00 /1M chars | |
| 32 | 31-36 | Falcon 2 | 1156±1295% interval 1144 to 1168 | 3,076 | Jul 2026 | $10.00 /1M chars | |
| 33 | 31-36 | Gradium TTS (Aug 2026) | 1153±1195% interval 1142 to 1164 | 3,135 | Aug 2026 | $47.78 /1M chars | |
| 34 | 31-37 | Falcon 2.1 | 1151±1595% interval 1136 to 1166 | 1,610 | Oct 2026 | $10.00 /1M chars | |
| 35 | 31-36 | Speech 2.8 Turbo | 1150±1095% interval 1140 to 1160 | 5,507 | Feb 2026 | $60.00 /1M chars | |
| 36 | 32-37 | Azure HD 2.5 | 1149±1195% interval 1138 to 1160 | 3,473 | Mar 2026 | $22.00 /1M chars | |
| 37 | 36-39 | Async Flash v1.5 | 1139±1195% interval 1128 to 1150 | 3,221 | May 2026 | $10.10 /1M chars | |
| 38 | 37-39 | Step TTS 2 (Mar 2026) | 1136±1195% interval 1125 to 1147 | 3,257 | Feb 2026 | $40.00 /1M chars | |
| 39 | 37-41 | Async Pro v1.0 | 1131±1195% interval 1120 to 1142 | 3,046 | May 2026 | $20.20 /1M chars | |
| 40 | 39-42 | Speech 2.6 HD | 1124±1095% interval 1114 to 1134 | 4,701 | Oct 2025 | $100.00 /1M chars | |
| 41 | 39-42 | Speech 2.6 Turbo | 1122±1095% interval 1112 to 1132 | 4,939 | Oct 2025 | $60.00 /1M chars | |
| 42 | 40-47 | Coda v2 | 1115±1395% interval 1102 to 1128 | 2,083 | Oct 2026 | $50.00 /1M chars | |
| 43 | 41-48 | Simba 3.0 | 1112±1195% interval 1101 to 1123 | 3,464 | Feb 2026 | $6.58 /1M chars | |
| 44 | 42-49 | TTS-1 HD | 1109±1195% interval 1098 to 1120 | 4,109 | Nov 2023 | $30.00 /1M chars | |
| 45 | 42-49 | Chatterbox HD | 1109±1195% interval 1098 to 1120 | 3,048 | — | May 2025 | $40.00 /1M chars |
| 46 | 42-49 | 1108±1395% interval 1095 to 1121 | 2,055 | Oct 2026 | $0.00 /1M chars | ||
| 47 | 43-51 | Speech-02-HD | 1104±1095% interval 1094 to 1114 | 4,973 | Mar 2025 | $100.00 /1M chars | |
| 48 | 43-53 | 1101±1195% interval 1090 to 1112 | 3,091 | Mar 2026 | $15.00 /1M chars | ||
| 49 | 44-53 | 1100±1195% interval 1089 to 1111 | 2,690 | Feb 2026 | N/A | ||
| 50 | 47-56 | 1094±1195% interval 1083 to 1105 | 2,833 | Mar 2026 | $16.00 /1M chars | ||
| 51 | 47-56 | Turbo v2.5 | 1094±1095% interval 1084 to 1104 | 7,338 | Jul 2024 | $50.00 /1M chars | |
| 52 | 48-57 | OpenAudio S1 | 1092±1195% interval 1081 to 1103 | 4,902 | Jun 2025 | $15.00 /1M chars | |
| 53 | 48-57 | Multilingual v2 | 1092±1095% interval 1082 to 1102 | 7,751 | Aug 2023 | $100.00 /1M chars | |
| 54 | 49-57 | Speech 2.6 | 1089±1195% interval 1078 to 1100 | 2,916 | Jul 2026 | N/A | |
| 55 | 50-57 | Speech-02-Turbo | 1088±1195% interval 1077 to 1099 | 4,316 | Mar 2025 | $60.00 /1M chars | |
| 56 | 50-57 | TTS-1 | 1086±1095% interval 1076 to 1096 | 6,576 | Nov 2023 | $15.00 /1M chars | |
| 57 | 52-61 | Gemini 2.5 Flash Lite TTS | 1082±1195% interval 1071 to 1093 | 3,568 | Dec 2025 | $9.15 /1M chars | |
| 58 | 57-63 | Flash v2.5 | 1075±1095% interval 1065 to 1085 | 6,085 | Dec 2024 | $50.00 /1M chars | |
| 59 | 57-64 | Studio | 1074±1195% interval 1063 to 1085 | 4,854 | Feb 2023 | $160.00 /1M chars | |
| 60 | 57-65 | T2A-01-HD | 1072±1195% interval 1061 to 1083 | 5,308 | Jan 2025 | $50.00 /1M chars | |
| 61 | 57-65 | Gemini 2.5 Flash TTS (Dec 2025) | 1072±1195% interval 1061 to 1083 | 3,184 | Dec 2025 | $9.15 /1M chars | |
| 62 | 58-70 | GPT-Realtime-2 | 1070±1295% interval 1058 to 1082 | 2,636 | May 2026 | $191.56 /1M chars | |
| 63 | 58-70 | Journey | 1067±1295% interval 1055 to 1079 | 2,577 | Dec 2023 | $160.00 /1M chars | |
| 64 | 58-70 | 1064±1295% interval 1052 to 1076 | 2,591 | Feb 2026 | N/A | ||
| 65 | 60-71 | Sonic 3 | 1062±1195% interval 1051 to 1073 | 3,794 | Oct 2025 | $49.00 /1M chars | |
| 66 | 62-71 | Polly Generative | 1061±1195% interval 1050 to 1072 | 4,045 | May 2024 | $30.00 /1M chars | |
| 67 | 62-72 | Chirp 3: HD | 1060±1195% interval 1049 to 1071 | 3,677 | Mar 2025 | $30.00 /1M chars | |
| 68 | 62-72 | 1060±1195% interval 1049 to 1071 | 5,672 | Jan 2025 | $0.65 /1M chars | ||
| 69 | 62-74 | Maya 2 Flash | 1058±1295% interval 1046 to 1070 | 2,524 | Jul 2026 | N/A | |
| 70 | 63-72 | Octave 2 | 1058±1195% interval 1047 to 1069 | 3,434 | Oct 2025 | $87.50 /1M chars | |
| 71 | 65-77 | Flux TTS | 1052±1295% interval 1040 to 1064 | 2,575 | Aug 2026 | $45.00 /1M chars | |
| 72 | 66-79 | Coda | 1049±1295% interval 1037 to 1061 | 2,780 | May 2026 | $50.00 /1M chars | |
| 73 | 69-79 | MiMo-V2.5-TTS | 1047±1295% interval 1035 to 1059 | 2,409 | - | N/A | |
| 74 | 69-79 | 1047±1295% interval 1035 to 1059 | 3,559 | Jun 2025 | N/A | ||
| 75 | 70-80 | Maya 2 Global | 1046±1295% interval 1034 to 1058 | 2,311 | Jul 2026 | N/A | |
| 76 | 71-80 | Async Flash v1.0 | 1045±1195% interval 1034 to 1056 | 4,296 | Jul 2025 | $10.10 /1M chars | |
| 77 | 65-86 | 1042±2095% interval 1022 to 1062 | 1,678 | Jun 2025 | $15.00 /1M chars | ||
| 78 | 72-83 | Octave TTS | 1038±1195% interval 1027 to 1049 | 4,897 | Feb 2025 | $87.50 /1M chars | |
| 79 | 72-83 | Gemini 2.5 Pro (Dec 2025) | 1038±1295% interval 1026 to 1050 | 2,674 | Dec 2025 | $18.31 /1M chars | |
| 80 | 75-86 | 1035±1295% interval 1023 to 1047 | 2,470 | Jun 2026 | $15.00 /1M chars | ||
| 81 | 77-86 | Bland Speech v3 | 1032±1295% interval 1020 to 1044 | 2,922 | Aug 2026 | $40.00 /1M chars | |
| 82 | 71-87 | Azure Neural | 1032±2095% interval 1012 to 1052 | 1,156 | Sept 2018 | $15.00 /1M chars | |
| 83 | 78-87 | Polly Long-Form | 1028±1395% interval 1015 to 1041 | 2,162 | Nov 2023 | $100.00 /1M chars | |
| 84 | 80-87 | Lightning v3.1 | 1025±1295% interval 1013 to 1037 | 2,614 | Mar 2026 | $25.00 /1M chars | |
| 85 | 80-87 | MAI-Voice-1 | 1024±1295% interval 1012 to 1036 | 2,549 | Apr 2026 | N/A | |
| 86 | 80-87 | T2A-01-Turbo | 1024±1195% interval 1013 to 1035 | 5,178 | Jan 2025 | $30.00 /1M chars | |
| 87 | 83-87 | 1019±1195% interval 1008 to 1030 | 4,899 | May 2025 | $25.00 /1M chars | ||
| 88 | 88-89 | Raon SpeechLM | 1006±1395% interval 993 to 1019 | 2,513 | Apr 2026 | N/A | |
| 89 | 89 | 1000AnchorFixed at 1000 as the reference point for this board's Elo scale. | 5,029 | Feb 2025 | $20.00 /1M chars | ||
| 90 | 90 | Murf Speech Gen 2 | 986±1295% interval 974 to 998 | 5,158 | Jul 2024 | $100.00 /1M chars | |
| 91 | 91-92 | 954±1395% interval 941 to 967 | 3,188 | — | Apr 2024 | $8.33 /1M chars | |
| 92 | 91-92 | 954±1495% interval 940 to 968 | 2,252 | Aug 2025 | N/A | ||
| 93 | 93-95 | Qwen3 TTS Flash | 940±1495% interval 926 to 954 | 2,296 | Sept 2025 | $11.03 /1M chars | |
| 94 | 93-96 | Neuphonic TTS | 939±1495% interval 925 to 953 | 2,572 | Oct 2024 | $20.79 /1M chars | |
| 95 | 93-97 | Qwen3 TTS | 928±1395% interval 915 to 941 | 3,216 | Jan 2026 | $13.79 /1M chars | |
| 96 | 95-98 | Kugel 3 | 925±1395% interval 912 to 938 | 4,645 | Jun 2026 | N/A | |
| 97 | 96-98 | WaveNet | 916±1295% interval 904 to 928 | 6,472 | Sept 2016 | $4.00 /1M chars | |
| 98 | 95-99 | 914±1595% interval 899 to 929 | 2,769 | — | Nov 2023 | $40.44 /1M chars | |
| 99 | 97-101 | Mist V2 | 902±1595% interval 887 to 917 | 3,134 | Mar 2025 | $31.13 /1M chars | |
| 100 | 99-103 | Polly Neural | 894±1495% interval 880 to 908 | 3,029 | Jul 2019 | $16.00 /1M chars | |
| 101 | 99-103 | Neural2 | 891±1295% interval 879 to 903 | 6,748 | Jun 2022 | $16.00 /1M chars | |
| 102 | 100-103 | 887±1595% interval 872 to 902 | 2,764 | — | Jun 2023 | $2.82 /1M chars | |
| 103 | 100-103 | Standard | 884±1395% interval 871 to 897 | 6,824 | Aug 2018 | $4.00 /1M chars | |
| 104 | 104 | Noiz TTS | 866±1495% interval 852 to 880 | 2,569 | Nov 2025 | N/A | |
| 105 | 105-106 | 845±1895% interval 827 to 863 | 1,717 | — | Feb 2024 | N/A | |
| 106 | 105-106 | Polly Standard | 830±1695% interval 814 to 846 | 3,646 | 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 Turbo (Elo 1340), 2. Eleven v4 (Elo 1340), 3. StepAudio 3 TTS (Elo 1307), 4. Qwen-Audio-3.1-TTS-Plus (Elo 1298), and 5. Sonic 3.6 (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 1060. 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 1277), 2. Fish Audio Drama 3 Preview (Elo 1237), 3. Breeze TTS 2 (Elo 1228), 4. Ming-3.0-tts (Elo 1179), and 5. Phonon 31M (English) (Elo 1108).