Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Technical report on the Step-Audio speech models by StepFun's Step-Audio Team; arXiv 2502.11946, version 1 of 17 February 2025 cited.
- Issued by
- StepFun / 阶跃星辰
- Authors credited
- No authorship claim recorded yet. The source records list Step-Audio Team, StepFun.
- Dates
- Published 2025-02-17 issue evidence
- Exact source
- Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction (arXiv abstract page, v1) arXiv · published 2025-02-17 · Dated document, retrieved on 2026-10-29 (SHA-256 c0e354ce34395d92fcf56a81a70afcba6d308e5d678d5fd989732c4a59f87549) directly from the publisher. Version: 2502.11946v1. Abstract page of version 1 (submitted 2025-02-17); the page lists a later version v2 (18 February 2025), not inspected.
- Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction (arXiv PDF, v1) arXiv · published 2025-02-17 · Dated document, retrieved on 2026-10-29 (SHA-256 73f7cd03586ac6f7cc10630c2f944cc95f4a50e9063f31a4018de84dbc7a89eb) directly from the publisher. Version: 2502.11946v1. PDF of version 1; later versions not inspected.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.