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 | 81 | 103,153 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%81 Votes103,153 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 85 | 95,395 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%85 Votes95,395 | ||||||||
| 🥉 | MusicGen | 89 | 78 | 92,353 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%78 Votes92,353 | ||||||||
| 4 | AudioCraft | 88 | 86 | 96,702 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%86 Votes96,702 | ||||||||
| 5 | Bark | 86 | 71 | 86,840 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%71 Votes86,840 | ||||||||
| 6 | Voicebox | 84 | 79 | 90,905 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%79 Votes90,905 | ||||||||
| 7 | AudioLM | 83 | 77 | 84,609 | Proprietary | 7 AudioLMScore83 Win%77 Votes84,609 | |||||||||
| 8 | Vall-E | 81 | 83 | 88,076 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%83 Votes88,076 | ||||||||
| 9 | Tortoise TTS | 79 | 77 | 79,390 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%77 Votes79,390 | ||||||||
| 10 | Coqui TTS | 76 | 63 | 80,618 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%63 Votes80,618 | ||||||||