Data‑Driven Analysis of Text‑Conditioning in AI‑Generated Music: A Case Study with Suno and Udio

Luca Casini; Laura Cros Vila; David Dalmazzo; Anna-Kaisa Kaila; Bob L.T. Sturm

doi:10.5334/tismir.273

Data‑Driven Analysis of Text‑Conditioning in AI‑Generated Music: A Case Study with Suno and Udio

Transactions of the International Society for Music Information Retrieval

Volume 9 (2026): Issue 1

By: Luca Casini, Laura Cros Vila, David Dalmazzo, Anna-Kaisa Kaila and Bob L.T. Sturm

Open Access

|May 2026

Abstract

Online commercial artificial intelligence (AI) platforms for generating music from text prompts (AI music) are now being used by many users to create millions of music audio recordings daily. Some AI music is appearing in advertising, music playlists of restaurants and gyms, and even hit music charts, in many countries. How are users engaging with these text‑to‑music AI platforms, where text is a principal mode of interaction to specify prompts (e.g., free terms), lyrics (e.g., sung terms), and tags (e.g., high‑level stylistic terms)? What languages appear? What characterizes prompts, lyrics, and tags? How are mentions of real artists used? What kind of additional instructions (metatags) are used? To address these questions, we assemble and analyze a collection of 101, 953 songs generated from May to October 2024 by 60, 342 users of Suno and Udio. Using a combination of state‑of‑the‑art text‑embedding models, dimensionality reduction, and clustering methods, we analyze the prompts, tags, and lyrics and automatically annotate and display the processed data in interactive plots. Our results reveal prominent themes in lyrics, language preferences, and prompting strategies, as well as peculiar attempts at steering models through the use of metatags. We share our code and data resources to promote further musicological study of AI music.

References

Åkestam Holst. (2024). Åkestam holst creates entire Italian ‘80s pop culture universe to sell swedish cinnamon buns. Little Black Book.
Search in Google Scholar Back to article
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., Nori, H., Palangi, H., Ribeiro, M. T., and Zhang, Y. (2023). Sparks of artificial general intelligence: Early experiments with GPT‑4. arXiv preprint arXiv:2303.12712.
Search in Google Scholar Back to article
Campello, R. J., Moulavi, D., and Sander, J. (2013). Density‑based clustering based on hierarchical density estimates. In Pacific‑Asia Conference on Knowledge Discovery and Data Mining (pp. 160–172). Springer.
Search in Google Scholar Back to article
Deruty, E., Grachten, M., Lattner, S., Nistal, J., and Aouameur, C. (2022). On the development and practice of AI technology for contemporary popular music production. Transactions of the International Society for Music Information Retrieval, 5(1), 35–49.
Search in Google Scholar Back to article
Ester, M., Kriegel, H.‑P., Sander, J., and Xu, X. (1996). A density‑based algorithm for discovering clusters in large spatial databases with noise. In KDD’96: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (Vol. 96, pp. 226–231).
Search in Google Scholar Back to article
European Union. (2019, May 17). Directive (EU) 2019/790 of the European Parliament and of the Council of 17 April 2019 on copyright and related rights in the digital single market. Official Journal of the European Union, L 130, 92–125.
Search in Google Scholar Back to article
Fell, M., and Sporleder, C. (2014). Lyrics‑based analysis and classification of music. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers (pp. 620–631).
Search in Google Scholar Back to article
Goldmedia. (2024). AI and music: Market development of AI in the music sector and impact on music authors and creators in germany and france. Technical report, GEMA and SACEM. Research report commissioned by GEMA and SACEM.
Search in Google Scholar Back to article
Herington, J., Borasi, R., Guerroro, B. J., Miller, D. E., Koerner, B., Jan, Y. J., Borys, Z., and Roberts, R. (2025). Musicians’ ethical concerns about AI: An interview study. AI & Society.
Search in Google Scholar Back to article
Kehagia, N., and Moriaty, M. (2023). Recurring patterns: An ethnographic study on the adoption of AI music tools by practitioners of electroacoustic, contemporary and popular musics. Journal of Pervasive Media, 8.
Search in Google Scholar Back to article
Klevjer, C. A. (2024). Står bak noregs første KI‑hit – nrk kultur og underholdning. 16471806. https://www.nrk.no/kultur/star-bak-noregs-forste-ki-hit-1.
Search in Google Scholar Back to article
Kriisa, A. (2024). Ai‑generated song tops swedish charts ‑ kulturnytt | swedish radio. https://sverigesradio.se/artikel/AI-genererad-lat-toppar-svensk-topplista.
Search in Google Scholar Back to article
Lee, C., Roy, R., Xu, M., Raiman, J., Shoeybi, M., Catanzaro, B., and Ping, W. (2024). NV‑Embed: Improved techniques for training llms as generalist embedding models. arXiv preprint arXiv:2405.17428.
Search in Google Scholar Back to article
Logan, B., Kositsky, A., and Moreno, P. (2004). Semantic analysis of song lyrics. In 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No. 04TH8763) (Vol. 2, pp. 827–830). IEEE.
Search in Google Scholar Back to article
Mayer, R., and Rauber, A. (2010). Multimodal aspects of music retrieval: Audio, song lyrics ‑ and beyond? Studies in Computational Intelligence, 274, 333–363.
Search in Google Scholar Back to article
Mayer, R., and Rauber, A. (2011). Music genre classification by ensembles of audio and lyrics features. In The 12th International Society for Music Information Retrieval Conference, Miami, Florida (USA) October 24–28, 2011 (pp. 675–680).
Search in Google Scholar Back to article
McCormack, J., Llano, M. T., Krol, S. J., and Rajcic, N. (2024). No longer trending on artstation: Prompt analysis of generative AI art. In International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar) (pp. 279–295). Springer.
Search in Google Scholar Back to article
McInnes, L., Healy, J., and Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.
Search in Google Scholar Back to article
Napier, K., and Shamir, L. (2018). Quantitative sentiment analysis of lyrics in popular music. Journal of Popular Music Studies, 30(4), 161–176.
Search in Google Scholar Back to article
Oppenlaender, J., Linder, R., and Silvennoinen, J. (2024). Prompting AI art: An investigation into the creative skill of prompt engineering. International Journal of Human–Computer Interaction, 1–23.
Search in Google Scholar Back to article
Parada‑Cabaleiro, E., Mayerl, M., Brandl, S., Skowron, M., Schedl, M., Lex, E., and Zangerle, E. (2024). Song lyrics have become simpler and more repetitive over the last five decades. Scientific Reports, 14(1), 5531.
Search in Google Scholar Back to article
Pyrovolakis, K., Tzouveli, P., and Stamou, G. (2022). Multi‑modal song mood detection with deep learning. Sensors, 22(3), 1065.
Search in Google Scholar Back to article
Rahman, M. A., Hakim, Z. I. A., Sarker, N. H., Paul, B., and Fattah, S. A. (2024). Sonics: Synthetic or not–identifying counterfeit songs. arXiv preprint arXiv:2408.14080.
Search in Google Scholar Back to article
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical text‑conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2), 3.
Search in Google Scholar Back to article
Robinson, K. (2025). Suno creates an entire spotify catalog’s worth of music every two weeks, says investor pitch deck for $250m fundraise. webiste.
Search in Google Scholar Back to article
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022). High‑resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684–10695).
Search in Google Scholar Back to article
Sanchez, T. (2023). Examining the text‑to‑image community of practice: Why and how do people prompt generative AIs? In Proceedings of the 15th Conference on Creativity and Cognition, C&C ’23 (pp. 43–61). New York, NY, USA; Association for Computing Machinery.
Search in Google Scholar Back to article
Simpson, W. (2024). The first ever AI‑generated track to hit the charts has landed in Germany, and people aren’t happy. musicradar. https://www.musicradar.com/news/first-ever-AI-chart-germany.
Search in Google Scholar Back to article
Sturm, B. L., Déguernel, K., Huang, R. S., Kaila, A.‑K., Jääskeläinen, P., Kanhov, E., Vila, L. C., Dalmazzo, D., Casini, L., Bown, O. R., Collins, N., Drott, E., Sterne, J., Holzapfel, A., and Ben‑Tal, O. (2024). AI music studies: Preparing for the coming flood. In AI Music Creativity.
Search in Google Scholar Back to article
Tan, S. (2024). Are we all musicians now? Authenticity, musicianship, and AI music generator suno. OSF.
Search in Google Scholar Back to article
Torres, A. J. R., Alberto, J. M. C., Guieb, A. P. J., and Villarama, J. A. (2025). Language, identity, and ethics in AI‑driven art: Perspectives from human artists in digital environments. Language, Technology, and Social Media, 3(1), 17–29.
Search in Google Scholar Back to article
Varnum, M. E., Krems, J. A., Morris, C., Wormley, A., and Grossmann, I. (2021). Why are song lyrics becoming simpler? A time series analysis of lyrical complexity in six decades of american popular music. PloS One, 16(1), e0244576.
Search in Google Scholar Back to article
Wang, Z. J., Montoya, E., Munechika, D., Yang, H., Hoover, B., and Chau, D. H. (2022). Large‑scale prompt gallery dataset for text‑to‑image generative models. arXiv:2210. 14896 [cs].
Search in Google Scholar Back to article
Yang, P. (2025). Inside suno: The AI music app you won’t stop listening to.
Search in Google Scholar Back to article

Articles in this issue

DOI: https://doi.org/10.5334/tismir.273 | Journal eISSN: 2514-3298

Journal RSS Feed

Language: English

Page range: 194 - 209

Submitted on: Apr 30, 2025

Accepted on: Apr 3, 2026

Published on: May 7, 2026

Published by: Ubiquity Press

In partnership with: Paradigm Publishing Services

Publication frequency: 1 issue per year

Keywords:

AI music,

generative AI,

Suno,

Udio,

exploratory data analysis,

natural language processing

© 2026 Luca Casini, Laura Cros Vila, David Dalmazzo, Anna-Kaisa Kaila, Bob L.T. Sturm, published by Ubiquity Press
This work is licensed under the Creative Commons Attribution 4.0 License.

Volume 9 (2026): Issue 1