Claim · 2025-07-22 · publication · Stated in source · Supported

A StepFun team posted the Step-Audio 2 Technical Report to arXiv on 22 July 2025 (version 1), describing Step-Audio 2, an end-to-end multimodal model for audio understanding and speech conversation.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

StepFun / 阶跃星辰 → published → Step-Audio 2 Technical Report

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

StepFun / 阶跃星辰published ↓Step-Audio 2 Technical Report

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 2 sources

Date: 2025-07-22 · publication Records dated 2025 →

Scope and limitsThe report is the developer's own description; performance and benchmark claims in it are out of scope. Credit to StepFun rests on the team line of the report, not on a separate statement of ownership.

The evidence 02

primary sourceSupports the claim

Step-Audio 2 Technical Report (arXiv PDF, v1)

arXiv · 2025-07-22

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“Step-Audio 2 Technical Report StepFun Audio Team”

Location in source Title page

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: StepFun Audio Team
Version: Dated document, retrieved on 2026-10-29 (SHA-256 355405ed474290dbe7e394c8230a8e383f424947d4e83f2378299327def33ad0) directly from the publisher. Version: 2507.16632v1. PDF of version 1; later versions not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: StepFun Audio Team, “Step-Audio 2 Technical Report (arXiv PDF, v1)”, 2025-07-22.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (7 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

primary sourceSupports the claim

Step-Audio 2 Technical Report (arXiv abstract page, v1)

arXiv · 2025-07-22

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation”

Location in source arXiv abstract page, abstract

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: StepFun Audio Team
Version: Dated document, retrieved on 2026-10-29 (SHA-256 54d4147bea0ef91ca6b1b4888b6be69ce3676a279c3bffcb35bcb6b015580e8d) directly from the publisher. Version: 2507.16632v1. Abstract page of version 1 (submitted 2025-07-22); the page lists later versions v2 (24 July 2025) and v3 (27 August 2025), not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: StepFun Audio Team, “Step-Audio 2 Technical Report (arXiv abstract page, v1)”, 2025-07-22.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (14 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. Publication of a specific document or version. Publication of a policy is not evidence of implementation.

Date. Submission date of the cited arXiv version; not the model's release date and not the date of later versions.

Record ID c3-stepfun-step-audio-2-report