| Paper | Code | Content | Emotion | Prosody | Paralinguistic | Acoustic | Style | Compositional | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|
| dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model | ✓ Link | 94.5 | 3.29 | 89.33 | 9.0 | 32.4 | 40.67 | 6.5 | dots.tts.edit | 2026-08-02 |
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 91.83 | 9.94 | 71.33 | 38.5 | 37.07 | AuK | 2026-09-08 | ||
| AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing | ✓ Link | 87.5 | 6.29 | 70.0 | 39.25 | 30.26 | AuK-Flash | 2026-09-08 | ||
| SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing | ✓ Link | 76.46 | 3.43 | 26.5 | 11.25 | 25.85 | 22.17 | 1.76 | Ming-UniAudio | 2026-06-03 |
| SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing | ✓ Link | 16.5 | 7.71 | 20.13 | 31.25 | 22.89 | 49.67 | 2.01 | Step-Audio-EditX | 2026-06-03 |