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 | 80 | 97,651 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%80 Votes97,651 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 93 | 103,507 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%93 Votes103,507 | ||||||||
| 🥉 | MusicGen | 89 | 88 | 98,324 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%88 Votes98,324 | ||||||||
| 4 | AudioCraft | 88 | 71 | 93,454 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%71 Votes93,454 | ||||||||
| 5 | Bark | 86 | 71 | 88,959 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%71 Votes88,959 | ||||||||
| 6 | Voicebox | 84 | 72 | 89,938 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%72 Votes89,938 | ||||||||
| 7 | AudioLM | 83 | 74 | 88,263 | Proprietary | 7 AudioLMScore83 Win%74 Votes88,263 | |||||||||
| 8 | Vall-E | 81 | 76 | 86,415 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%76 Votes86,415 | ||||||||
| 9 | Tortoise TTS | 79 | 82 | 88,001 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%82 Votes88,001 | ||||||||
| 10 | Coqui TTS | 76 | 76 | 77,010 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%76 Votes77,010 | ||||||||