| Paper | Code | ZH Deletion WER | EN Insertion WER | EN Deletion SIM | EN Deletion WER | ZH Insertion SIM | ZH Insertion WER | EN Substitution WER | EN Insertion SIM | ZH Deletion SIM | EN Substitution SIM | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Fish Audio Drama 3 Technical Report | ✓ Link | 7.82 | 3.03 | 0.838 | 5.79 | 0.909 | 2.15 | 2.08 | 0.905 | 0.827 | 0.866 | Fish Audio Drama 3 | 2026-10-13 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 9.61 | 3.47 | 0.83 | 5.91 | 0.92 | 3.03 | 2.18 | 0.92 | 0.8 | 0.89 | AuK | 2026-09-08 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 9.85 | 4.26 | 0.84 | 7.38 | 0.93 | 3.6 | 2.48 | 0.8 | AuK-Flash | 2026-09-08 | ||
| FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation | ✓ Link | 10.82 | 4.98 | 0.79 | 12.78 | 0.83 | 3.28 | 4.46 | 0.84 | 0.81 | FireRedAudio | 2026-08-25 | |
| Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation | ✓ Link | 11.89 | 6.63 | 0.76 | 14.85 | 0.83 | 3.42 | 8.99 | 0.79 | 0.78 | 0.78 | Ming-UniAudio | 2025-10-26 |