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 | 78 | 107,161 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%78 Votes107,161 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 79 | 103,158 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%79 Votes103,158 | ||||||||
| 🥉 | MusicGen | 89 | 82 | 95,287 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%82 Votes95,287 | ||||||||
| 4 | AudioCraft | 88 | 83 | 95,036 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%83 Votes95,036 | ||||||||
| 5 | Bark | 86 | 84 | 95,739 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%84 Votes95,739 | ||||||||
| 6 | Voicebox | 84 | 85 | 86,526 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%85 Votes86,526 | ||||||||
| 7 | AudioLM | 83 | 68 | 87,745 | Proprietary | 7 AudioLMScore83 Win%68 Votes87,745 | |||||||||
| 8 | Vall-E | 81 | 84 | 81,840 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%84 Votes81,840 | ||||||||
| 9 | Tortoise TTS | 79 | 69 | 79,388 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%69 Votes79,388 | ||||||||
| 10 | Coqui TTS | 76 | 80 | 79,453 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%80 Votes79,453 | ||||||||