# StepAudio 3 Music Technical Report

arXiv: https://arxiv.org/abs/2609.16034 · HTML: https://mlsanity.com/paper/2609.16034/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 25 of 25)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Long-form music generation with latent diffusion](https://mlsanity.com/paper/2404.10301/) (2024)
- [ChatMusician: Understanding and Generating Music Intrinsically with LLM](https://mlsanity.com/paper/2402.16153/) (2024)
- [MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization](https://mlsanity.com/paper/2501.01108/) (2025)
- [ACE-Step: A Step Towards Music Generation Foundation Model](https://mlsanity.com/paper/2506.00045/) (2025)
- [FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration](https://mlsanity.com/paper/2501.14350/) (2025)
- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation](https://mlsanity.com/paper/2406.10970/) (2024)
- [ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation](https://mlsanity.com/paper/2602.00744/) (2026)
- [InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models](https://mlsanity.com/paper/2308.14360/) (2023)
- [Seed-Music: A Unified Framework for High Quality and Controlled Music Generation](https://mlsanity.com/paper/2409.09214/) (2024)
- [DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation](https://mlsanity.com/paper/2505.13000/) (2025)
- [SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision](https://mlsanity.com/paper/2510.02797/) (2025)
- [FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System](https://mlsanity.com/paper/2603.10420/) (2026)
- [Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation](https://mlsanity.com/paper/2503.19611/) (2025)
- [InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation](https://mlsanity.com/paper/2503.00084/) (2025)
- [SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment](https://mlsanity.com/paper/2604.25937/) (2026)
- [Qwen-Music Technical Report](https://mlsanity.com/paper/2607.11699/) (2026)
- [Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering](https://mlsanity.com/paper/2607.20253/) (2026)

## Built on by (most cited first, 1 of 1)

- [MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent](https://mlsanity.com/paper/2610.10355/) (2026)

## Abstract (arXiv)

We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation. The StepAudio Music Tokenizer represents audio as a 50-Hz stream from a 65536-entry single codebook, using semantically informed self-supervised and multi-task training to preserve musical structure and reconstruction-relevant information. A flow-matching diffusion Transformer (DiT) predicts continuous StepAudio VAE latents, which our VAE decoder converts into 48-kHz audio. This discrete-continuous design is guided by comparisons of single-codebook VQ, Semantic and Acoustic RVQ, and different DiT configurations. For explicit planning, a Mixture-of-Experts autoregressive model uses ABC notation to produce an intermediate arrangement plan (ABC-CoT) before predicting music tokens, making harmony, rhythm, and melodic structure part of the generation context. A progressive training curriculum and supervised fine-tuning support song and instrumental generation, accompaniment generation from dry vocals, and cover-song synthesis for up to 5 minutes and 30 seconds. With reinforcement learning via direct preference optimization (DPO), the final model achieves the highest AudioBox Content Enjoyment, Content Usefulness, and Production Quality scores and the highest MuQ-MuLan similarity among the evaluated systems, with competitive SongBench results. On the preliminary Artificial Analysis Music Arena Vocals leaderboard, it obtains a Quality Elo of 1105, behind only Suno V5.5 and Mureka and ahead of Suno V5, MiniMax models, and other systems. Audio demonstrations are available at https://stepaudiollm.github.io/step-audio-3-music.