Audio Processing
Speech recognition, text-to-speech, and audio generation models
Last Updated
Nov 9, 2025
Total Votes
85,830
Total Models
10
Single Column
| Rank (UB) | Model | Score | Win% [?] | Votes | Organization | License | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 🥇 | Whisper Large v3 | 97 | 89 | 105,742 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%89 Votes105,742 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 87 | 102,121 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%87 Votes102,121 | ||||||||
| 🥉 | MusicGen | 89 | 81 | 97,366 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%81 Votes97,366 | ||||||||
| 4 | AudioCraft | 88 | 79 | 92,843 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%79 Votes92,843 | ||||||||
| 5 | Bark | 86 | 72 | 93,783 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%72 Votes93,783 | ||||||||
| 6 | Voicebox | 84 | 73 | 86,244 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%73 Votes86,244 | ||||||||
| 7 | AudioLM | 83 | 81 | 88,841 | Proprietary | 7 AudioLMScore83 Win%81 Votes88,841 | |||||||||
| 8 | Vall-E | 81 | 72 | 88,447 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%72 Votes88,447 | ||||||||
| 9 | Tortoise TTS | 79 | 68 | 88,015 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%68 Votes88,015 | ||||||||
| 10 | Coqui TTS | 76 | 76 | 82,973 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%76 Votes82,973 | ||||||||