# Fast Text-to-Audio Generation with Adversarial Post-Training

arXiv: https://arxiv.org/abs/2505.08175 · HTML: https://mlsanity.com/paper/2505.08175/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 30 of 42)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models](https://mlsanity.com/paper/2410.11081/) (2024)
- [Query-Key Normalization for Transformers](https://mlsanity.com/paper/2010.04245/) (2020)
- [Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation](https://mlsanity.com/paper/2403.12015/) (2024)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs](https://mlsanity.com/paper/2311.09257/) (2023)
- [Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis](https://mlsanity.com/paper/2404.13686/) (2024)
- [Diffusion Adversarial Post-Training for One-Step Video Generation](https://mlsanity.com/paper/2501.08316/) (2025)
- [CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models](https://mlsanity.com/paper/2406.08070/) (2024)
- [Consistency Models Made Easy](https://mlsanity.com/paper/2406.14548/) (2024)

## Built on by (most cited first, 14 of 14)

- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [Live Music Models](https://mlsanity.com/paper/2508.04651/) (2025)
- [Music Arena: Live Evaluation for Text-to-Music](https://mlsanity.com/paper/2507.20900/) (2025)
- [Stable Audio 3](https://mlsanity.com/paper/2605.17991/) (2026)
- [SoundReactor: Frame-level Online Video-to-Audio Generation](https://mlsanity.com/paper/2510.02110/) (2025)
- [TuneJury: An Open Metric for Improving Music Generation Preference Alignment](https://mlsanity.com/paper/2606.17006/) (2026)
- [Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation](https://mlsanity.com/paper/2507.17937/) (2025)
- [V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation](https://mlsanity.com/paper/2603.11042/) (2026)
- [Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators](https://mlsanity.com/paper/2605.22717/) (2026)
- [WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling](https://mlsanity.com/paper/2507.10534/) (2025)
- [Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation](https://mlsanity.com/paper/2603.01565/) (2026)
- [SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving](https://mlsanity.com/paper/2603.07865/) (2026)
- [Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis](https://mlsanity.com/paper/2605.14555/) (2026)
- [Continuous Adversarial MeanFlow Transfer](https://mlsanity.com/paper/2608.19540/) (2026)

## Abstract (arXiv)

Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first adversarial acceleration algorithm for diffusion/flow models not based on distillation. While past adversarial post-training methods have struggled to compare against their expensive distillation counterparts, ARC post-training is a simple procedure that (1) extends a recent relativistic adversarial formulation to diffusion/flow post-training and (2) combines it with a novel contrastive discriminator objective to encourage better prompt adherence. We pair ARC post-training with a number optimizations to Stable Audio Open and build a model capable of generating ≈12s of 44.1kHz stereo audio in ≈75ms on an H100, and ≈7s on a mobile edge-device, the fastest text-to-audio model to our knowledge.