Tabla de clasificación de la Arena de voz controladaArtificial Analysis
Compara modelos de texto a voz (TTS) usando las mismas 8 voces clonadas (4 de EE. UU., 4 del Reino Unido).
Range | Creator | Model | Elo | 95% CI | Samples | Lanzamiento | Precio de API 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1-2 | Sonic 3.6 | 1117 | -16/16 | 1,797 | Aug 2026 | 49,0 US$ /1 M de caracteres | |
| 2 | 1-2 | Realtime TTS-2 | 1110 | -16/16 | 1,626 | Aug 2026 | 20,8 US$ /1 M de caracteres | |
| 3 | 3 | Sonic 3.5 | 1088 | -13/13 | 3,451 | May 2026 | 49,0 US$ /1 M de caracteres | |
| 4 | 4 | Realtime TTS-2 Flash | 1071 | -15/15 | 1,623 | Aug 2026 | 10,4 US$ /1 M de caracteres | |
| 5 | 5-7 | Eleven v3 | 1048 | -13/13 | 2,997 | Feb 2026 | 100,0 US$ /1 M de caracteres | |
| 6 | 5-7 | StepAudio 2.5 TTS | 1045 | -14/14 | 2,362 | Apr 2026 | 85,0 US$ /1 M de caracteres | |
| 7 | 5-9 | SpaceXAI TTS | 1036 | -14/14 | 2,317 | Mar 2026 | 15,0 US$ /1 M de caracteres | |
| 8 | 7-10 | v3 Conversational | 1025 | -15/15 | 1,525 | Aug 2026 | 50,0 US$ /1 M de caracteres | |
| 9 | 7-10 | Speech 2.8 HD | 1024 | -13/13 | 2,870 | Feb 2026 | 100,0 US$ /1 M de caracteres | |
| 10 | 9-14 | Speech 2.8 Turbo | 1012 | -13/13 | 2,963 | Feb 2026 | 60,0 US$ /1 M de caracteres | |
| 11 | 10-18 | Simba 3.0 | 1009 | -14/14 | 2,263 | Feb 2026 | 6,6 US$ /1 M de caracteres | |
| 12 | 10-19 | Breeze TTS 2 | 1007 | -15/15 | 1,635 | Aug 2026 | 34,0 US$ /1 M de caracteres | |
| 13 | 10-19 | Multilingual v2 | 1004 | -13/13 | 2,850 | Aug 2023 | 100,0 US$ /1 M de caracteres | |
| 14 | 14 | OpenAudio S1 | 1000 | 0/0 | 4,767 | Jun 2025 | 15,0 US$ /1 M de caracteres | |
| 15 | 10-20 | OpenAudio S1 Mini | 998 | -14/14 | 2,257 | Jun 2025 | 15,0 US$ /1 M de caracteres | |
| 16 | 11-20 | Voxtral TTS | 997 | -14/14 | 2,204 | Mar 2026 | 16,0 US$ /1 M de caracteres | |
| 17 | 11-20 | Fish Audio S2.1 Pro | 997 | -14/14 | 2,249 | Jun 2026 | 15,0 US$ /1 M de caracteres | |
| 18 | 11-20 | Gradium TTS (Aug 2026) | 996 | -15/15 | 1,768 | Aug 2026 | 47,2 US$ /1 M de caracteres | |
| 19 | 13-20 | Fish Audio S2 Pro | 993 | -13/13 | 3,432 | Mar 2026 | 15,0 US$ /1 M de caracteres | |
| 20 | 14-20 | Fish Audio S1 | 989 | -13/13 | 2,978 | Oct 2025 | 15,0 US$ /1 M de caracteres | |
| 21 | 21-23 | Flash v2.5 | 974 | -13/13 | 2,898 | Dec 2024 | 50,0 US$ /1 M de caracteres | |
| 22 | 21-23 | Turbo v2.5 | 972 | -14/14 | 2,392 | Jul 2024 | 50,0 US$ /1 M de caracteres | |
| 23 | 21-23 | Kugel 3 | 965 | -13/13 | 3,636 | Jun 2026 | N/D | |
| 24 | 24-25 | Higgs Audio V3 TTS | 946 | -14/14 | 2,017 | Jun 2026 | 15,0 US$ /1 M de caracteres | |
| 25 | 24-27 | Sonic 3 | 936 | -14/14 | 2,488 | Oct 2025 | 49,0 US$ /1 M de caracteres | |
| 26 | 25-30 | Chatterbox | 926 | -14/14 | 2,415 | May 2025 | 25,0 US$ /1 M de caracteres | |
| 27 | 25-30 | Magpie TTS ZeroshotOpen Weights | 924 | -17/17 | 892 | Jul 2026 | N/D | |
| 28 | 25-30 | Raon SpeechLM | 921 | -15/15 | 1,615 | Apr 2026 | N/D | |
| 29 | 26-30 | Soniox TTS Real-Time v2 | 918 | -15/15 | 1,680 | Aug 2026 | 14,2 US$ /1 M de caracteres | |
| 30 | 26-30 | Noiz TTS | 916 | -15/15 | 1,981 | Nov 2025 | N/D | |
| 31 | 31 | Lightning v3.1 | 886 | -15/15 | 2,064 | Mar 2026 | 25,0 US$ /1 M de caracteres | |
| 32 | 32 | XTTS v2 | 829 | -16/16 | 2,249 | Nov 2023 | 40,4 US$ /1 M de caracteres | |
| 33 | 33 | OpenVoice v2 | 784 | -17/17 | 1,973 | Apr 2024 | 8,3 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