Provider Voice Arena LeaderboardArtificial Analysis
Compare Text to Speech (TTS) models using each provider's own native voices.
Range | Creator | Model | Elo | 95% CI | Samples | Arena Voices | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1-3 |  Cartesia | Sonic 3.6 | 1273 | -17/17 | 1,757 | Aug 2026 | $49.0 /1M chars | |
| 2 | 1-4 |  Google | Gemini 3.8 Flash TTS | 1260 | -17/17 | 1,999 | Sept 2026 | $33.0 /1M chars | |
| 3 | 1-4 |  Alibaba | Qwen-Audio-3.0-TTS-Plus | 1259 | -17/17 | 1,447 | Sept 2026 | $27.6 /1M chars | |
| 4 | 2-7 |  Inworld | Realtime TTS-2 | 1245 | -18/18 | 1,239 | Aug 2026 | $20.8 /1M chars | |
| 5 | 4-7 |  SpeechifyAI | Simba 3.2 | 1237 | -14/14 | 2,391 | Jul 2026 | $6.6 /1M chars | |
| 6 | 4-7 | Google | Gemini 3.8 Flash-Lite TTS | 1235 | -16/16 | 2,000 | Sept 2026 | $22.1 /1M chars | |
| 7 | 5-7 |  VUI Labs | Luna TTS | 1230 | -14/14 | 2,511 | Jun 2026 | $15.0 /1M chars | |
| 8 | 8-12 | Inworld | Realtime TTS-2 Flash | 1210 | -15/15 | 1,691 | Aug 2026 | $10.4 /1M chars | |
| 9 | 8-12 |  BreezeBlue | Breeze TTS 2  Open Weights | 1204 | -16/16 | 1,390 | Aug 2026 | $34.0 /1M chars | |
| 10 | 8-12 | Google | Gemini 3.1 Flash TTS | 1199 | -12/12 | 3,430 | Apr 2026 | $18.3 /1M chars | |
| 11 | 8-13 |  StepFun | StepAudio 2.5 TTS (Aug 2026) | 1199 | -17/17 | 1,279 | Aug 2026 | $85.0 /1M chars | |
| 12 | 8-13 |  ElevenLabs | v3 Conversational | 1196 | -15/15 | 1,844 | Aug 2026 | $50.0 /1M chars | |
| 13 | 12-14 | Cartesia | Sonic 3.5 | 1185 | -12/12 | 2,994 | May 2026 | $49.0 /1M chars | |
| 14 | 13-17 |  Smallest.ai | Lightning V3.1 Pro (Jul 2026) | 1175 | -14/14 | 1,912 | Jul 2026 | $19.5 /1M chars | |
| 15 | 14-17 |  Soniox | Soniox TTS Real-Time v2 | 1173 | -12/12 | 4,615 | Aug 2026 | $14.2 /1M chars | |
| 16 | 14-18 |  MiniMax | Speech 2.8 HD | 1168 | -11/11 | 4,414 | Feb 2026 | $100.0 /1M chars | |
| 17 | 14-18 | ElevenLabs | Eleven v3 | 1167 | -11/11 | 4,345 | Feb 2026 | $100.0 /1M chars | |
| 18 | 16-20 |  Murf AI | Falcon 2 | 1157 | -15/15 | 1,740 | Jul 2026 | $10.0 /1M chars | |
| 19 | 18-21 | MiniMax | Speech 2.8 Turbo | 1149 | -11/11 | 4,318 | Feb 2026 | $60.0 /1M chars | |
| 20 | 18-21 |  Gradium | Gradium TTS (Aug 2026) | 1148 | -14/14 | 1,661 | Aug 2026 | $47.2 /1M chars | |
| 21 | 19-26 |  Fish Audio | Fish Audio S2.1 Pro | 1139 | -13/13 | 2,162 | Jun 2026 | $15.0 /1M chars | |
| 22 | 21-28 | StepFun | Step TTS 2 (Mar 2026) | 1131 | -13/13 | 2,213 | Feb 2026 | $40.0 /1M chars | |
| 23 | 21-28 |  Microsoft | Azure HD 2.5 | 1128 | -12/12 | 2,405 | Mar 2026 | $22.0 /1M chars | |
| 24 | 21-30 |  SpaceXAI | SpaceXAI TTS | 1128 | -15/15 | 1,210 | Mar 2026 | $15.0 /1M chars | |
| 25 | 21-28 |  async | Async Flash v1.5 | 1128 | -13/13 | 2,098 | May 2026 | $10.1 /1M chars | |
| 26 | 21-28 | MiniMax | Speech 2.6 HD | 1127 | -12/12 | 3,833 | Oct 2025 | $100.0 /1M chars | |
| 27 | 22-31 | Fish Audio | Fish Audio S2 Pro Open Weights | 1120 | -13/13 | 2,213 | Mar 2026 | $15.0 /1M chars | |
| 28 | 23-31 | SpeechifyAI | Simba 3.0 | 1118 | -12/12 | 2,480 | Feb 2026 | $6.6 /1M chars | |
| 29 | 27-31 | MiniMax | Speech 2.6 Turbo | 1114 | -11/11 | 4,177 | Oct 2025 | $60.0 /1M chars | |
| 30 | 27-31 | async | Async Pro v1.0 | 1113 | -13/13 | 2,009 | May 2026 | $20.2 /1M chars | |
| 31 | 27-32 | MiniMax | Speech-02-HD | 1111 | -12/12 | 4,246 | Mar 2025 | $100.0 /1M chars | |
| 32 | 31-37 |  OpenAI | TTS-1 HD | 1099 | -12/12 | 3,473 | Nov 2023 | $30.0 /1M chars | |
| 33 | 32-39 |  Resemble AI | Chatterbox HD | 1096 | -13/13 | 2,305 | — | May 2025 | $40.0 /1M chars |
| 34 | 32-39 |  Hithink | Speech 2.6 | 1096 | -13/13 | 1,952 | Jul 2026 | N/A | |
| 35 | 32-39 | ElevenLabs | Turbo v2.5 | 1095 | -11/11 | 6,753 | Jul 2024 | $50.0 /1M chars | |
| 36 | 32-39 | StepFun | Step Audio EditX (Mar 2026) Open Weights | 1094 | -13/13 | 1,927 | Feb 2026 | N/A | |
| 37 | 32-39 | ElevenLabs | Multilingual v2 | 1092 | -10/10 | 7,199 | Aug 2023 | $100.0 /1M chars | |
| 38 | 33-43 | OpenAI | TTS-1 | 1086 | -11/11 | 6,033 | Nov 2023 | $15.0 /1M chars | |
| 39 | 33-45 | MiniMax | Speech-02-Turbo | 1085 | -12/12 | 3,706 | Mar 2025 | $60.0 /1M chars | |
| 40 | 37-46 | Google | Gemini 2.5 Flash Lite TTS | 1081 | -12/12 | 3,064 | Dec 2025 | $9.2 /1M chars | |
| 41 | 38-47 | Fish Audio | OpenAudio S1 | 1077 | -11/11 | 4,413 | Jun 2025 | $15.0 /1M chars | |
| 42 | 38-47 |  Mistral | Voxtral TTS Open Weights | 1076 | -13/13 | 2,036 | Mar 2026 | $16.0 /1M chars | |
| 43 | 38-47 | Google | Studio | 1075 | -12/12 | 4,364 | Feb 2023 | $160.0 /1M chars | |
| 44 | 39-47 | ElevenLabs | Flash v2.5 | 1074 | -11/11 | 5,605 | Dec 2024 | $50.0 /1M chars | |
| 45 | 38-51 | Google | Journey | 1073 | -13/13 | 2,175 | Dec 2023 | $160.0 /1M chars | |
| 46 | 39-51 | OpenAI | GPT-Realtime-2 | 1072 | -13/13 | 1,976 | May 2026 | $191.6 /1M chars | |
| 47 | 41-53 |  Maya Research | Maya 2 Flash | 1066 | -14/14 | 1,819 | Jul 2026 | N/A | |
| 48 | 43-55 |  NVIDIA | Magpie-Multilingual 357M (Feb 2026) Open Weights | 1063 | -13/13 | 1,971 | Feb 2026 | N/A | |
| 49 | 46-55 |  Kokoro | Kokoro 82M v1.0 Open Weights | 1061 | -11/11 | 5,232 | Jan 2025 | $0.7 /1M chars | |
| 50 | 47-55 | MiniMax | T2A-01-HD | 1061 | -11/11 | 4,878 | Jan 2025 | $50.0 /1M chars | |
| 51 | 46-58 |  Amazon | Polly Generative | 1061 | -12/12 | 3,654 | May 2024 | $30.0 /1M chars | |
| 52 | 47-59 | Cartesia | Sonic 3 | 1056 | -12/12 | 3,413 | Oct 2025 | $49.0 /1M chars | |
| 53 | 47-59 |  Rime | Coda | 1054 | -13/13 | 2,188 | May 2026 | $50.0 /1M chars | |
| 54 | 48-61 | Google | Chirp 3: HD | 1052 | -12/12 | 3,271 | Mar 2025 | $30.0 /1M chars | |
| 55 | 48-61 | Google | Gemini 2.5 Flash TTS (Dec 2025) | 1051 | -12/12 | 2,804 | Dec 2025 | $9.2 /1M chars | |
| 56 | 49-61 | async | Async Flash v1.0 | 1049 | -12/12 | 3,951 | Jul 2025 | $10.1 /1M chars | |
| 57 | 50-61 |  Hume AI | Octave 2 | 1049 | -12/12 | 3,020 | Oct 2025 | $87.5 /1M chars | |
| 58 | 49-61 |  Xiaomi | MiMo-V2.5-TTS | 1049 | -13/13 | 1,865 | - | N/A | |
| 59 | 52-63 | Maya Research | Maya 2 Global | 1047 | -14/14 | 1,677 | Jul 2026 | N/A | |
| 60 | 52-71 | Fish Audio | OpenAudio S1 Mini Open Weights | 1041 | -20/20 | 1,681 | Jun 2025 | $15.0 /1M chars | |
| 61 | 54-66 | Maya Research | Maya1 Open Weights | 1041 | -12/12 | 3,205 | Jun 2025 | N/A | |
| 62 | 60-71 |  Bland AI | Bland Speech v3 | 1033 | -13/13 | 2,242 | Aug 2026 | $40.0 /1M chars | |
| 63 | 60-71 |  Boson AI | Higgs Audio V3 TTS Open Weights | 1033 | -13/13 | 1,970 | Jun 2026 | $15.0 /1M chars | |
| 64 | 60-72 | Amazon | Polly Long-Form | 1032 | -13/13 | 1,889 | Nov 2023 | $100.0 /1M chars | |
| 65 | 56-72 | Microsoft | Azure Neural | 1031 | -19/19 | 1,158 | Sept 2018 | $15.0 /1M chars | |
| 66 | 60-72 | Microsoft | MAI-Voice-1 | 1030 | -13/13 | 2,134 | Apr 2026 | N/A | |
| 67 | 62-72 | Hume AI | Octave TTS | 1027 | -12/12 | 4,617 | Feb 2025 | $87.5 /1M chars | |
| 68 | 62-72 | MiniMax | T2A-01-Turbo | 1027 | -11/11 | 4,905 | Jan 2025 | $30.0 /1M chars | |
| 69 | 62-72 | Google | Gemini 2.5 Pro (Dec 2025) | 1027 | -13/13 | 2,403 | Dec 2025 | $18.3 /1M chars | |
| 70 | 65-72 | Resemble AI | Chatterbox  Open Weights | 1021 | -11/11 | 4,600 | May 2025 | $25.0 /1M chars | |
| 71 | 62-72 | Xiaomi | MiMo-V2-TTS | 1021 | -14/14 | 1,716 | Mar 2026 | N/A | |
| 72 | 64-72 | Smallest.ai | Lightning v3.1 | 1020 | -13/13 | 2,089 | Mar 2026 | $25.0 /1M chars | |
| 73 | 73-75 |  Krafton | Raon SpeechLM | 1002 | -14/14 | 2,028 | Apr 2026 | N/A | |
| 74 | 73-75 | Rime | Arcana v3 | 1000 | -13/13 | 2,179 | Feb 2026 | $50.0 /1M chars | |
| 75 | 75 |  Zyphra | Zonos-v0.1 Open Weights | 1000 | 0/0 | 4,802 | Feb 2025 | $20.0 /1M chars | |
| 76 | 76 | Murf AI | Murf Speech Gen 2 | 983 | -12/12 | 4,969 | Jul 2024 | $100.0 /1M chars | |
| 77 | 77-79 | Microsoft | VibeVoice 1.5B Open Weights | 951 | -14/14 | 2,095 | Aug 2025 | N/A | |
| 78 | 77-80 |  OpenVoice | OpenVoice v2 Open Weights | 946 | -13/13 | 2,968 | Apr 2024 | $8.3 /1M chars | |
| 79 | 77-81 | Alibaba | Qwen3 TTS Flash | 941 | -14/14 | 2,117 | Sept 2025 | $10.0 /1M chars | |
| 80 | 78-82 |  Neuphonic | Neuphonic TTS | 936 | -14/14 | 2,380 | Oct 2024 | $20.8 /1M chars | |
| 81 | 79-82 |  KugelAudio | Kugel 3 | 931 | -13/13 | 4,132 | Jun 2026 | N/A | |
| 82 | 80-84 | Alibaba | Qwen3 TTS | 926 | -13/13 | 2,861 | Jan 2026 | $20.0 /1M chars | |
| 83 | 82-85 | Google | WaveNet | 915 | -12/12 | 6,225 | Sept 2016 | $4.0 /1M chars | |
| 84 | 82-85 |  Coqui | XTTS v2 Open Weights | 914 | -15/15 | 2,523 | — | Nov 2023 | $40.4 /1M chars |
| 85 | 83-87 | Rime | Mist V2 | 906 | -15/15 | 2,825 | Mar 2025 | $31.1 /1M chars | |
| 86 | 86-88 | Google | Neural2 | 894 | -12/12 | 6,455 | Jun 2022 | $16.0 /1M chars | |
| 87 | 85-90 |  StyleTTS | StyleTTS 2 Open Weights | 891 | -15/15 | 2,437 | — | Jun 2023 | $2.8 /1M chars |
| 88 | 86-90 | Amazon | Polly Neural | 890 | -14/14 | 2,735 | Jul 2019 | $16.0 /1M chars | |
| 89 | 87-90 | Google | Standard | 881 | -12/12 | 6,491 | Aug 2018 | $4.0 /1M chars | |
| 90 | 86-90 |  Noiz | Noiz TTS | 881 | -15/15 | 1,958 | Nov 2025 | N/A | |
| 91 | 91-92 |  MetaVoice | MetaVoice v1 Open Weights | 845 | -18/18 | 1,349 | — | Feb 2024 | N/A |
| 92 | 92 | Amazon | Polly Standard | 828 | -16/16 | 3,286 | 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. Sonic 3.6 (Elo 1273), 2. Gemini 3.8 Flash TTS (Elo 1260), 3. Qwen-Audio-3.0-TTS-Plus (Elo 1259), 4. Realtime TTS-2 (Elo 1245), and 5. Simba 3.2 (Elo 1237). 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. Breeze TTS 2 (Elo 1204), 2. Fish Audio S2 Pro (Elo 1120), 3. Step Audio EditX (Mar 2026) (Elo 1094), 4. Voxtral TTS (Elo 1076), and 5. Magpie-Multilingual 357M (Feb 2026) (Elo 1063).