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 | 83 | 102,011 | OpenAI | Proprietary | 🥇 Whisper Large v3OpenAI Score97 Win%83 Votes102,011 | ||||||||
| 🥈 | ElevenLabs v2 | 95 | 89 | 103,948 | ElevenLabs | Proprietary | 🥈 ElevenLabs v2ElevenLabs Score95 Win%89 Votes103,948 | ||||||||
| 🥉 | MusicGen | 89 | 81 | 97,456 | Meta | Proprietary | 🥉 MusicGenMeta Score89 Win%81 Votes97,456 | ||||||||
| 4 | AudioCraft | 88 | 83 | 89,253 | Meta | Proprietary | 4 AudioCraftMeta Score88 Win%83 Votes89,253 | ||||||||
| 5 | Bark | 86 | 76 | 86,587 | Suno AI | Proprietary | 5 BarkSuno AI Score86 Win%76 Votes86,587 | ||||||||
| 6 | Voicebox | 84 | 82 | 91,054 | Meta | Proprietary | 6 VoiceboxMeta Score84 Win%82 Votes91,054 | ||||||||
| 7 | AudioLM | 83 | 78 | 91,966 | Proprietary | 7 AudioLMScore83 Win%78 Votes91,966 | |||||||||
| 8 | Vall-E | 81 | 79 | 89,193 | Microsoft | Proprietary | 8 Vall-EMicrosoft Score81 Win%79 Votes89,193 | ||||||||
| 9 | Tortoise TTS | 79 | 67 | 81,442 | Open Source | Proprietary | 9 Tortoise TTSOpen Source Score79 Win%67 Votes81,442 | ||||||||
| 10 | Coqui TTS | 76 | 74 | 79,912 | Coqui | Proprietary | 10 Coqui TTSCoqui Score76 Win%74 Votes79,912 | ||||||||