Tabla de clasificación de la Arena de voz del proveedorArtificial Analysis
Compara modelos de texto a voz (TTS) usando las voces nativas de cada proveedor.
Range | Creator | Model | Elo | 95% CI | Samples | Voces de la Arena | Lanzamiento | Precio de API 1 | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1 |  Cartesia | Sonic 3.6 | 1275 | -17/17 | 1,755 | Aug 2026 | 49,0 US$ /1 M de caracteres | |
| 2 | 2-5 |  Inworld | Realtime TTS-2 | 1244 | -19/19 | 1,091 | Aug 2026 | 20,8 US$ /1 M de caracteres | |
| 3 | 2-5 |  SpeechifyAI | Simba 3.2 | 1233 | -14/14 | 2,320 | Jul 2026 | 6,6 US$ /1 M de caracteres | |
| 4 | 2-5 |  Alibaba | Qwen-Audio-3.0-TTS-Plus | 1232 | -14/14 | 2,306 | Jul 2026 | 27,6 US$ /1 M de caracteres | |
| 5 | 3-5 |  VUI Labs | Luna TTS | 1229 | -14/14 | 2,464 | Jun 2026 | 80,0 US$ /1 M de caracteres | |
| 6 | 6-9 | Inworld | Realtime TTS-2 Flash | 1211 | -16/16 | 1,626 | Aug 2026 | 10,4 US$ /1 M de caracteres | |
| 7 | 6-10 |  BreezeBlue | Breeze TTS 2  Open Weights | 1205 | -17/17 | 1,227 | Aug 2026 | 34,0 US$ /1 M de caracteres | |
| 8 | 6-10 |  StepFun | StepAudio 2.5 TTS (Aug 2026) | 1204 | -17/17 | 1,105 | Aug 2026 | 85,0 US$ /1 M de caracteres | |
| 9 | 6-10 |  Google | Gemini 3.1 Flash TTS | 1202 | -12/12 | 3,405 | Apr 2026 | 18,3 US$ /1 M de caracteres | |
| 10 | 7-12 |  ElevenLabs | v3 Conversational | 1194 | -16/16 | 1,721 | Aug 2026 | 50,0 US$ /1 M de caracteres | |
| 11 | 10-13 | Cartesia | Sonic 3.5 | 1184 | -12/12 | 3,043 | May 2026 | 49,0 US$ /1 M de caracteres | |
| 12 | 10-14 |  Smallest.ai | Lightning V3.1 Pro (Jul 2026) | 1182 | -15/15 | 1,881 | Jul 2026 | 19,5 US$ /1 M de caracteres | |
| 13 | 11-15 |  Soniox | Soniox TTS Real-Time v2 | 1176 | -12/12 | 5,079 | Aug 2026 | 14,2 US$ /1 M de caracteres | |
| 14 | 13-15 |  MiniMax | Speech 2.8 HD | 1168 | -11/11 | 4,443 | Feb 2026 | 100,0 US$ /1 M de caracteres | |
| 15 | 13-16 | ElevenLabs | Eleven v3 | 1166 | -11/11 | 4,374 | Feb 2026 | 100,0 US$ /1 M de caracteres | |
| 16 | 14-18 |  Murf AI | Falcon 2 | 1156 | -15/15 | 1,592 | Jul 2026 | 10,0 US$ /1 M de caracteres | |
| 17 | 16-18 | MiniMax | Speech 2.8 Turbo | 1151 | -11/11 | 4,334 | Feb 2026 | 60,0 US$ /1 M de caracteres | |
| 18 | 16-22 |  Gradium | Gradium TTS (Aug 2026) | 1143 | -15/15 | 1,563 | Aug 2026 | 47,2 US$ /1 M de caracteres | |
| 19 | 17-24 |  Fish Audio | Fish Audio S2.1 Pro | 1139 | -13/13 | 2,139 | Jun 2026 | 15,0 US$ /1 M de caracteres | |
| 20 | 18-24 | StepFun | Step TTS 2 (Mar 2026) | 1136 | -13/13 | 2,256 | Feb 2026 | 40,0 US$ /1 M de caracteres | |
| 21 | 18-26 |  SpaceXAI | SpaceXAI TTS | 1134 | -16/16 | 1,152 | Mar 2026 | 15,0 US$ /1 M de caracteres | |
| 22 | 18-25 |  async | Async Flash v1.5 | 1133 | -13/13 | 2,175 | May 2026 | 10,1 US$ /1 M de caracteres | |
| 23 | 19-26 |  Microsoft | Azure HD 2.5 | 1128 | -12/12 | 2,497 | Mar 2026 | 22,0 US$ /1 M de caracteres | |
| 24 | 20-27 | MiniMax | Speech 2.6 HD | 1126 | -11/11 | 3,933 | Oct 2025 | 100,0 US$ /1 M de caracteres | |
| 25 | 21-29 | Fish Audio | Fish Audio S2 Pro Open Weights | 1122 | -13/13 | 2,257 | Mar 2026 | 15,0 US$ /1 M de caracteres | |
| 26 | 23-29 | MiniMax | Speech 2.6 Turbo | 1118 | -11/11 | 4,307 | Oct 2025 | 60,0 US$ /1 M de caracteres | |
| 27 | 24-30 | SpeechifyAI | Simba 3.0 | 1116 | -12/12 | 2,541 | Feb 2026 | 6,6 US$ /1 M de caracteres | |
| 28 | 26-30 | MiniMax | Speech-02-HD | 1111 | -11/11 | 4,284 | Mar 2025 | 100,0 US$ /1 M de caracteres | |
| 29 | 25-31 | async | Async Pro v1.0 | 1110 | -13/13 | 2,092 | May 2026 | 20,2 US$ /1 M de caracteres | |
| 30 | 27-31 |  OpenAI | TTS-1 HD | 1104 | -12/12 | 3,527 | Nov 2023 | 30,0 US$ /1 M de caracteres | |
| 31 | 29-35 | StepFun | Step Audio EditX (Mar 2026) Open Weights | 1098 | -13/13 | 2,004 | Feb 2026 | N/D | |
| 32 | 31-36 | ElevenLabs | Multilingual v2 | 1092 | -10/10 | 7,277 | Aug 2023 | 100,0 US$ /1 M de caracteres | |
| 33 | 31-37 | ElevenLabs | Turbo v2.5 | 1092 | -11/11 | 6,848 | Jul 2024 | 50,0 US$ /1 M de caracteres | |
| 34 | 31-42 |  Hithink | Speech 2.6 | 1088 | -13/13 | 1,899 | Jul 2026 | N/D | |
| 35 | 31-43 |  Resemble AI | Chatterbox HD | 1086 | -13/13 | 2,345 | — | May 2025 | 40,0 US$ /1 M de caracteres |
| 36 | 32-43 | OpenAI | TTS-1 | 1083 | -11/11 | 6,096 | Nov 2023 | 15,0 US$ /1 M de caracteres | |
| 37 | 32-43 | MiniMax | Speech-02-Turbo | 1081 | -12/12 | 3,760 | Mar 2025 | 60,0 US$ /1 M de caracteres | |
| 38 | 34-43 | Google | Studio | 1079 | -11/11 | 4,458 | Feb 2023 | 160,0 US$ /1 M de caracteres | |
| 39 | 34-43 | ElevenLabs | Flash v2.5 | 1078 | -11/11 | 5,672 | Dec 2024 | 50,0 US$ /1 M de caracteres | |
| 40 | 34-43 | Fish Audio | OpenAudio S1 | 1078 | -11/11 | 4,455 | Jun 2025 | 15,0 US$ /1 M de caracteres | |
| 41 | 34-43 | Google | Gemini 2.5 Flash Lite TTS | 1077 | -12/12 | 3,140 | Dec 2025 | 9,2 US$ /1 M de caracteres | |
| 42 | 34-44 | Google | Journey | 1076 | -13/13 | 2,216 | Dec 2023 | 160,0 US$ /1 M de caracteres | |
| 43 | 35-46 |  Mistral | Voxtral TTS Open Weights | 1074 | -13/13 | 2,104 | Mar 2026 | 16,0 US$ /1 M de caracteres | |
| 44 | 41-52 | OpenAI | GPT-Realtime-2 | 1065 | -13/13 | 1,993 | May 2026 | 191,6 US$ /1 M de caracteres | |
| 45 | 42-56 |  Maya Research | Maya 2 Flash | 1063 | -14/14 | 1,794 | Jul 2026 | N/D | |
| 46 | 44-53 | MiniMax | T2A-01-HD | 1062 | -11/11 | 4,911 | Jan 2025 | 50,0 US$ /1 M de caracteres | |
| 47 | 44-56 | Cartesia | Sonic 3 | 1060 | -12/12 | 3,510 | Oct 2025 | 49,0 US$ /1 M de caracteres | |
| 48 | 44-56 |  Amazon | Polly Generative | 1060 | -12/12 | 3,675 | May 2024 | 30,0 US$ /1 M de caracteres | |
| 49 | 44-56 |  Rime | Coda | 1059 | -13/13 | 2,185 | May 2026 | 50,0 US$ /1 M de caracteres | |
| 50 | 44-56 |  Kokoro | Kokoro 82M v1.0 Open Weights | 1059 | -11/11 | 5,278 | Jan 2025 | 0,7 US$ /1 M de caracteres | |
| 51 | 44-56 |  NVIDIA | Magpie-Multilingual 357M (Feb 2026) Open Weights | 1057 | -13/13 | 2,000 | Feb 2026 | N/D | |
| 52 | 44-58 |  Hume AI | Octave 2 | 1053 | -12/12 | 3,064 | Oct 2025 | 87,5 US$ /1 M de caracteres | |
| 53 | 45-59 |  Xiaomi | MiMo-V2.5-TTS | 1051 | -13/13 | 1,961 | - | N/D | |
| 54 | 46-59 | Google | Chirp 3: HD | 1051 | -12/12 | 3,368 | Mar 2025 | 30,0 US$ /1 M de caracteres | |
| 55 | 45-60 | Maya Research | Maya 2 Global | 1049 | -14/14 | 1,712 | Jul 2026 | N/D | |
| 56 | 47-60 | Google | Gemini 2.5 Flash TTS (Dec 2025) | 1049 | -12/12 | 2,891 | Dec 2025 | 9,2 US$ /1 M de caracteres | |
| 57 | 52-62 | async | Async Flash v1.0 | 1043 | -11/11 | 4,055 | Jul 2025 | 10,1 US$ /1 M de caracteres | |
| 58 | 52-64 | Amazon | Polly Long-Form | 1043 | -13/13 | 1,918 | Nov 2023 | 100,0 US$ /1 M de caracteres | |
| 59 | 48-67 | Fish Audio | OpenAudio S1 Mini Open Weights | 1040 | -20/20 | 1,681 | Jun 2025 | 15,0 US$ /1 M de caracteres | |
| 60 | 55-67 | Maya Research | Maya1 Open Weights | 1037 | -12/12 | 3,244 | Jun 2025 | N/D | |
| 61 | 57-67 |  Boson AI | Higgs Audio V3 TTS Open Weights | 1034 | -13/13 | 2,000 | Jun 2026 | 15,0 US$ /1 M de caracteres | |
| 62 | 57-67 |  Bland AI | Bland Speech v3 | 1034 | -13/13 | 2,251 | Aug 2026 | 40,0 US$ /1 M de caracteres | |
| 63 | 57-69 | Microsoft | MAI-Voice-1 | 1031 | -13/13 | 2,198 | Apr 2026 | N/D | |
| 64 | 55-70 | Microsoft | Azure Neural | 1031 | -19/19 | 1,158 | Sept 2018 | 15,0 US$ /1 M de caracteres | |
| 65 | 59-70 | Google | Gemini 2.5 Pro (Dec 2025) | 1028 | -12/12 | 2,474 | Dec 2025 | 18,3 US$ /1 M de caracteres | |
| 66 | 60-70 | MiniMax | T2A-01-Turbo | 1028 | -11/11 | 4,960 | Jan 2025 | 30,0 US$ /1 M de caracteres | |
| 67 | 60-70 | Hume AI | Octave TTS | 1027 | -11/11 | 4,681 | Feb 2025 | 87,5 US$ /1 M de caracteres | |
| 68 | 65-70 | Resemble AI | Chatterbox  Open Weights | 1019 | -11/11 | 4,638 | May 2025 | 25,0 US$ /1 M de caracteres | |
| 69 | 63-70 | Smallest.ai | Lightning v3.1 | 1019 | -13/13 | 2,186 | Mar 2026 | 25,0 US$ /1 M de caracteres | |
| 70 | 63-72 | Xiaomi | MiMo-V2-TTS | 1018 | -14/14 | 1,762 | Mar 2026 | N/D | |
| 71 | 70-73 |  Krafton | Raon SpeechLM | 1005 | -14/14 | 1,968 | Apr 2026 | N/D | |
| 72 | 71-73 | Rime | Arcana v3 | 1004 | -13/13 | 2,226 | Feb 2026 | 50,0 US$ /1 M de caracteres | |
| 73 | 73 |  Zyphra | Zonos-v0.1 Open Weights | 1000 | 0/0 | 4,860 | Feb 2025 | 20,0 US$ /1 M de caracteres | |
| 74 | 74 | Murf AI | Murf Speech Gen 2 | 977 | -12/12 | 5,033 | Jul 2024 | 100,0 US$ /1 M de caracteres | |
| 75 | 75-76 | Microsoft | VibeVoice 1.5B Open Weights | 960 | -14/14 | 2,129 | Aug 2025 | N/D | |
| 76 | 75-77 |  OpenVoice | OpenVoice v2 Open Weights | 951 | -13/13 | 2,978 | — | Apr 2024 | 8,3 US$ /1 M de caracteres |
| 77 | 76-80 | Alibaba | Qwen3 TTS Flash | 941 | -14/14 | 2,143 | Sept 2025 | 10,0 US$ /1 M de caracteres | |
| 78 | 77-80 |  Neuphonic | Neuphonic TTS | 934 | -14/14 | 2,399 | Oct 2024 | 20,8 US$ /1 M de caracteres | |
| 79 | 77-80 |  KugelAudio | Kugel 3 | 930 | -13/13 | 4,063 | Jun 2026 | N/D | |
| 80 | 78-81 | Alibaba | Qwen3 TTS | 927 | -13/13 | 2,914 | Jan 2026 | 20,0 US$ /1 M de caracteres | |
| 81 | 81-82 | Google | WaveNet | 915 | -12/12 | 6,255 | Sept 2016 | 4,0 US$ /1 M de caracteres | |
| 82 | 80-83 |  Coqui | XTTS v2 Open Weights | 914 | -15/15 | 2,543 | — | Nov 2023 | 40,4 US$ /1 M de caracteres |
| 83 | 81-85 | Rime | Mist V2 | 902 | -15/15 | 2,853 | Mar 2025 | 31,1 US$ /1 M de caracteres | |
| 84 | 83-87 |  StyleTTS | StyleTTS 2 Open Weights | 893 | -15/15 | 2,449 | — | Jun 2023 | 2,8 US$ /1 M de caracteres |
| 85 | 83-87 | Google | Neural2 | 891 | -12/12 | 6,501 | Jun 2022 | 16,0 US$ /1 M de caracteres | |
| 86 | 84-88 | Amazon | Polly Neural | 887 | -14/14 | 2,791 | Jul 2019 | 16,0 US$ /1 M de caracteres | |
| 87 | 85-88 | Google | Standard | 880 | -12/12 | 6,523 | Aug 2018 | 4,0 US$ /1 M de caracteres | |
| 88 | 86-88 |  Noiz | Noiz TTS | 875 | -15/15 | 1,968 | Nov 2025 | N/D | |
| 89 | 89-90 |  MetaVoice | MetaVoice v1 Open Weights | 835 | -18/18 | 1,368 | — | Feb 2024 | N/D |
| 90 | 89-90 | Amazon | Polly Standard | 826 | -15/15 | 3,353 | Nov 2016 | 4,0 US$ /1 M de caracteres |
1 El precio de API refleja el costo de generar 1M de caracteres en la API del creador del modelo con la configuración predeterminada del modelo
Preguntas frecuentes
Los mejores modelos de texto a voz por puntaje Elo son: 1. Sonic 3.6 (Elo 1275), 2. Realtime TTS-2 (Elo 1244), 3. Simba 3.2 (Elo 1233), 4. Qwen-Audio-3.0-TTS-Plus (Elo 1232) y 5. Luna TTS (Elo 1229). Los rankings se basan en votos a ciegas de usuarios en la Arena de voz.
Kokoro 82M v1.0 es el más asequible a $0.65 por 1M de caracteres, con un puntaje Elo de 1059. Otras opciones asequibles incluyen StyleTTS 2 a $2.82 por 1M de caracteres.
Los 5 mejores modelos de texto a voz de pesos abiertos son: 1. Breeze TTS 2 (Elo 1205), 2. Fish Audio S2 Pro (Elo 1122), 3. Step Audio EditX (Mar 2026) (Elo 1098), 4. Voxtral TTS (Elo 1074) y 5. Kokoro 82M v1.0 (Elo 1059).