# StepFun's StepAudio 3 Gen Unifies TTS and Music

> A single discrete autoregressive model handles speech, voice design, sound effects, and music generation.

Published by The Open Weights on Sep 10, 2026. Canonical: https://theopenweights.com/news/stepaudio-3-gen-7rfm

## Key facts

- Company: StepFun
- Model: StepAudio 3 Gen
- Version: 3 Gen
- Category: Text → Speech
- Modalities: Music, Text → Speech
- License: Other (Open weights, commercial use allowed)
- Significance: notable
- Published: 2026-09-10
- Last verified: 2026-09-15
- Canonical URL: https://theopenweights.com/news/stepaudio-3-gen-7rfm

StepFun has published a technical report for StepAudio 3 Gen, an audio generation model that aims to collapse several traditionally separate tasks into a single system. Rather than stitching together specialized pipelines, the model treats text-to-speech, voice design, sound effects, and music generation as variations of one underlying problem: predicting discrete audio tokens autoregressively. The details are laid out in the [technical report on Hugging Face](https://huggingface.co/papers/2609.12945).

The unifying idea is a discrete autoregressive approach, where audio is represented as sequences of tokens and generated one step at a time, much like a language model produces text. This framing lets the same architecture cover a wide span of outputs—from natural spoken voices to designed timbres, ambient sound effects, and full musical passages.

## Why it matters

Audio tooling has long been fragmented, with distinct models for speech synthesis, voice cloning, foley, and music. A model that spans all of these could simplify how developers build audio features and reduce the overhead of maintaining multiple systems.

- Text-to-speech for natural spoken output
- Voice design for crafting custom timbres and speaker identities
- Sound effects generation
- Music generation

StepFun has been steadily expanding its StepAudio line, and this generation pushes toward a more general-purpose audio backbone. The report is the primary source of information for now; practical details such as licensing terms, parameter counts, and availability will shape how quickly the broader community can build on it.

## Get the model

- [HF Papers](https://huggingface.co/papers/2609.12945)

## Sources

- [StepAudio 3 Gen Technical Report](https://huggingface.co/papers/2609.12945) — HF Papers, Sep 10, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "StepFun's StepAudio 3 Gen Unifies TTS and Music", The Open Weights, Sep 10, 2026, https://theopenweights.com/news/stepaudio-3-gen-7rfm