# TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

arXiv: https://arxiv.org/abs/2412.21037 · HTML: https://mlsanity.com/paper/2412.21037/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 43 of its 54 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)
- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 30 of 43)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)

## Built on by (most cited first, 30 of 68)

- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation](https://mlsanity.com/paper/2508.16930/) (2025)
- [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://mlsanity.com/paper/2602.08794/) (2026)
- [JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation](https://mlsanity.com/paper/2602.19163/) (2026)
- [FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation](https://mlsanity.com/paper/2507.08557/) (2025)
- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [EnvSDD: Benchmarking Environmental Sound Deepfake Detection](https://mlsanity.com/paper/2505.19203/) (2025)
- [UALM: Unified Audio Language Model for Understanding, Generation and Reasoning](https://mlsanity.com/paper/2510.12000/) (2025)
- [Apollo: Unified Multi-Task Audio-Video Joint Generation](https://mlsanity.com/paper/2601.04151/) (2026)
- [JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment](https://mlsanity.com/paper/2507.20880/) (2025)
- [AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation](https://mlsanity.com/paper/2506.03126/) (2025)
- [Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers](https://mlsanity.com/paper/2510.04577/) (2025)
- [AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering](https://mlsanity.com/paper/2601.14728/) (2026)
- [SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering](https://mlsanity.com/paper/2508.03448/) (2025)
- [Stable Audio 3](https://mlsanity.com/paper/2605.17991/) (2026)
- [AudioMoG: Guiding Audio Generation with Mixture-of-Guidance](https://mlsanity.com/paper/2509.23727/) (2025)
- [MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation](https://mlsanity.com/paper/2512.10264/) (2025)
- [DRAGON: Distributional Rewards Optimize Diffusion Generative Models](https://mlsanity.com/paper/2504.15217/) (2025)
- [FlexSED: Towards Open-Vocabulary Sound Event Detection](https://mlsanity.com/paper/2509.18606/) (2025)
- [Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video](https://mlsanity.com/paper/2510.21581/) (2025)
- [Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions](https://mlsanity.com/paper/2602.05220/) (2026)
- [Woosh: A Sound Effects Foundation Model](https://mlsanity.com/paper/2604.01929/) (2026)
- [TuneJury: An Open Metric for Improving Music Generation Preference Alignment](https://mlsanity.com/paper/2606.17006/) (2026)
- [AudioStory: Generating Long-Form Narrative Audio with Large Language Models](https://mlsanity.com/paper/2508.20088/) (2025)
- [RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing](https://mlsanity.com/paper/2509.14003/) (2025)
- [Hear What Matters! Text-conditioned Selective Video-to-Audio Generation](https://mlsanity.com/paper/2512.02650/) (2025)
- [Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models](https://mlsanity.com/paper/2503.16853/) (2025)
- [DreamAudio: Customized Text-to-Audio Generation with Diffusion Models](https://mlsanity.com/paper/2509.06027/) (2025)
- [Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation](https://mlsanity.com/paper/2512.02457/) (2025)
- [Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding](https://mlsanity.com/paper/2601.14304/) (2026)

## Abstract (arXiv)

We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in just 3.7 seconds on a single A40 GPU. A key challenge in aligning TTA models lies in the difficulty of creating preference pairs, as TTA lacks structured mechanisms like verifiable rewards or gold-standard answers available for Large Language Models (LLMs). To address this, we propose CLAP-Ranked Preference Optimization (CRPO), a novel framework that iteratively generates and optimizes preference data to enhance TTA alignment. We demonstrate that the audio preference dataset generated using CRPO outperforms existing alternatives. With this framework, TangoFlux achieves state-of-the-art performance across both objective and subjective benchmarks. We open source all code and models to support further research in TTA generation.