# Probing Audio-Generation Capabilities of Text-Based Language Models

arXiv: https://arxiv.org/abs/2506.00003 · HTML: https://mlsanity.com/paper/2506.00003/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 4 May 2025.

## Builds on (most cited first, 6 of 6)

- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color](https://mlsanity.com/paper/2109.06129/) (2021)
- [A Vision Check-up for Language Models](https://mlsanity.com/paper/2401.01862/) (2024)
- [Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code](https://mlsanity.com/paper/2312.14856/) (2023)

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

- [TuneGenie: Reasoning-based LLM agents for preferential music generation](https://mlsanity.com/paper/2506.12083/) (2025)

## Abstract (arXiv)

How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in textual data. We employ a three-tier approach, progressively increasing the complexity of audio generation: 1) Musical Notes, 2) Environmental Sounds, and 3) Human Speech. To bridge the gap between text and audio, we leverage code as an intermediary, prompting LLMs to generate code that, when executed, produces the desired audio output. To evaluate the quality and accuracy of the generated audio, we employ FAD and CLAP scores. Our findings reveal that while LLMs can generate basic audio features, their performance deteriorates as the complexity of the audio increases. This suggests that while LLMs possess a latent understanding of the auditory world, their ability to translate this understanding into tangible audio output remains rudimentary. Further research into techniques that can enhance the quality and diversity of LLM-generated audio can lead to an improvement in the performance of text-based LLMs in generating audio.