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 | 94 | 99,919 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%94 Votes99,919 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 82 | 100,377 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%82 Votes100,377 | ||||||||
| 🥉 | MusicGen | 89 | 85 | 92,457 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%85 Votes92,457 | ||||||||
| 4 | AudioCraft | 88 | 70 | 96,526 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%70 Votes96,526 | ||||||||
| 5 | Bark | 86 | 81 | 87,486 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%81 Votes87,486 | ||||||||
| 6 | Voicebox | 84 | 85 | 90,333 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%85 Votes90,333 | ||||||||
| 7 | AudioLM | 83 | 81 | 91,883 | Proprietary | 7 AudioLMScore83 Win%81 Votes91,883 | |||||||||
| 8 | Vall-E | 81 | 66 | 84,539 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%66 Votes84,539 | ||||||||
| 9 | Tortoise TTS | 79 | 65 | 85,222 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%65 Votes85,222 | ||||||||
| 10 | Coqui TTS | 76 | 80 | 78,684 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%80 Votes78,684 | ||||||||