Bestenliste der Arena für kontrollierte StimmenArtificial Analysis
Vergleichen Sie Text-to-Speech-Modelle (TTS) mit denselben 8 geklonten Stimmen (4 US, 4 UK).
Range | Creator | Model | Elo | 95% CI | Samples | Veröffentlicht | API-Preise 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1-2 | Realtime TTS-2 | 1123 | -16/16 | 1,292 | Aug 2026 | 20,8 $ /1 Mio. Zeichen | |
| 2 | 1-2 | Sonic 3.6 | 1119 | -15/15 | 1,993 | Aug 2026 | 49,0 $ /1 Mio. Zeichen | |
| 3 | 3 | Sonic 3.5 | 1096 | -12/12 | 3,791 | May 2026 | 49,0 $ /1 Mio. Zeichen | |
| 4 | 4-5 | Realtime TTS-2 Flash - Research Preview | 1075 | -15/15 | 1,621 | Aug 2026 | 10,4 $ /1 Mio. Zeichen | |
| 5 | 5-6 | Eleven v3 | 1062 | -12/12 | 3,244 | Feb 2026 | 100,0 $ /1 Mio. Zeichen | |
| 6 | 5-6 | StepAudio 2.5 TTS | 1052 | -13/13 | 2,558 | Apr 2026 | 85,0 $ /1 Mio. Zeichen | |
| 7 | 7-8 | SpaceXAI TTS | 1039 | -13/13 | 2,524 | Mar 2026 | 15,0 $ /1 Mio. Zeichen | |
| 8 | 7-9 | Speech 2.8 HD | 1028 | -12/12 | 3,188 | Feb 2026 | 100,0 $ /1 Mio. Zeichen | |
| 9 | 7-11 | v3 Conversational | 1026 | -14/14 | 1,626 | Aug 2026 | 50,0 $ /1 Mio. Zeichen | |
| 10 | 9-14 | Speech 2.8 Turbo | 1015 | -12/12 | 3,207 | Feb 2026 | 60,0 $ /1 Mio. Zeichen | |
| 11 | 9-15 | Simba 3.0 | 1015 | -13/13 | 2,553 | Feb 2026 | 12,5 $ /1 Mio. Zeichen | |
| 12 | 10-20 | Breeze TTS 2 | 1007 | -15/15 | 1,546 | Aug 2026 | 34,0 $ /1 Mio. Zeichen | |
| 13 | 10-20 | Voxtral TTS | 1005 | -13/13 | 2,554 | Mar 2026 | 16,0 $ /1 Mio. Zeichen | |
| 14 | 10-20 | Multilingual v2 | 1005 | -12/12 | 3,140 | Aug 2023 | 100,0 $ /1 Mio. Zeichen | |
| 15 | 11-20 | Fish Audio S2 Pro | 1003 | -12/12 | 3,765 | Mar 2026 | 15,0 $ /1 Mio. Zeichen | |
| 16 | 16 | OpenAudio S1 | 1000 | 0/0 | 5,013 | Jun 2025 | 15,0 $ /1 Mio. Zeichen | |
| 17 | 12-20 | OpenAudio S1 Mini | 1000 | -13/13 | 2,592 | Jun 2025 | 15,0 $ /1 Mio. Zeichen | |
| 18 | 12-20 | Gradium TTS (Aug 2026) | 1000 | -14/14 | 2,134 | Aug 2026 | 47,2 $ /1 Mio. Zeichen | |
| 19 | 12-20 | Fish Audio S2.1 Pro | 999 | -13/13 | 2,556 | Jun 2026 | 15,0 $ /1 Mio. Zeichen | |
| 20 | 14-20 | Fish Audio S1 | 993 | -12/12 | 3,398 | Oct 2025 | 15,0 $ /1 Mio. Zeichen | |
| 21 | 21-24 | Flash v2.5 | 974 | -12/12 | 3,204 | Dec 2024 | 50,0 $ /1 Mio. Zeichen | |
| 22 | 21-25 | Turbo v2.5 | 970 | -13/13 | 2,796 | Jul 2024 | 50,0 $ /1 Mio. Zeichen | |
| 23 | 21-25 | Kugel 3 | 968 | -12/12 | 4,728 | Jun 2026 | k. A. | |
| 24 | 21-25 | Lightning V3.1 Pro TTS (Jun 2026) | 965 | -13/13 | 2,745 | Jun 2026 | 19,5 $ /1 Mio. Zeichen | |
| 25 | 22-25 | Higgs Audio V3 TTS | 957 | -13/13 | 2,448 | Jun 2026 | 15,0 $ /1 Mio. Zeichen | |
| 26 | 26-29 | Sonic 3 | 936 | -13/13 | 2,988 | Oct 2025 | 49,0 $ /1 Mio. Zeichen | |
| 27 | 26-31 | Chatterbox | 931 | -13/13 | 2,865 | May 2025 | 25,0 $ /1 Mio. Zeichen | |
| 28 | 26-32 | Magpie TTS ZeroshotOpen Weights | 928 | -16/16 | 1,061 | Jul 2026 | k. A. | |
| 29 | 26-32 | Noiz TTS | 924 | -13/13 | 2,296 | Nov 2025 | k. A. | |
| 30 | 27-32 | VibeVoice 7B | 919 | -13/13 | 2,809 | Aug 2025 | k. A. | |
| 31 | 27-32 | Raon SpeechLM | 918 | -15/15 | 1,619 | Apr 2026 | k. A. | |
| 32 | 27-32 | Soniox TTS Real-Time v2 | 917 | -15/15 | 1,590 | Aug 2026 | 14,2 $ /1 Mio. Zeichen | |
| 33 | 33 | Lightning v3.1 | 886 | -14/14 | 2,500 | Mar 2026 | 25,0 $ /1 Mio. Zeichen | |
| 34 | 34 | XTTS v2 | 824 | -14/14 | 2,807 | Nov 2023 | 40,4 $ /1 Mio. Zeichen | |
| 35 | 35 | OpenVoice v2 | 792 | -16/16 | 2,487 | Apr 2024 | 8,3 $ /1 Mio. Zeichen |
1 API-Preise spiegeln die Kosten wider, 1M Zeichen über die API des Modellerstellers mit den Standardeinstellungen des Modells zu erzeugen