In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement

Marcus Winter

doi:10.1007/978-3-032-16454-4_23

In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement

Marcus Winter

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

Abstract

This position paper presents an application concept adapting Retrieval Aug-mented Generation (RAG) for geographic contexts, and combining it with Text-to-Speech (TTS) technology to automate the creation of audio narrations for locative media experiences. By minimizing the costs for research and me-dia production, it addresses a critical barrier for archives to remediating their content and catering for audiences who are not able to, or not inclined to, read written materials. The application concept is contextualized in efforts to create alternative media representations that convey content in-situ to increase its relevance. It is illustrated with a prototype application aiming to engage peo-ple with their local history through audio narrations fictionalizing archive ma-terials related to their location. A discussion of technical and user interface as-pects offer insights into design considerations informing the prototype devel-opment.

Original language	English
Title of host publication	Computer-Human Interaction Research and Applications
Subtitle of host publication	9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings
Editors	Josef F. Krems, Hugo Plácido da Silva, Pietro Cipresso
Place of Publication	Cham
Publisher	Springer
Pages	403-413
Number of pages	11
Volume	3
ISBN (Electronic)	9783032164513
ISBN (Print)	9783032164537
DOIs	https://doi.org/10.1007/978-3-032-16454-4_23
Publication status	Published - 13 Feb 2026
Event	9th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2025) - Marbella, Spain Duration: 20 Oct 2025 → 21 Oct 2025 https://chira.scitevents.org/

Publication series

Name	Communications in Computer and Information Science
Volume	2836 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	9th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2025)
Country/Territory	Spain
City	Marbella
Period	20/10/25 → 21/10/25
Internet address	https://chira.scitevents.org/

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

Cultural heritage (CH)
Hyperlocal media
Location-based services
Accessibility
Archives
Large language model (LLM)
Retrieval Augmented Generation (RAG)
Text-to-Speech (TTS)

Access to Document

10.1007/978-3-032-16454-4_23

In-Situ Audio Experiences - accepted manuscriptAccepted author manuscript, 470 KBLicence: CC BY

Cite this

Winter, M. (2026). In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement. In J. F. Krems, H. P. da Silva, & P. Cipresso (Eds.), Computer-Human Interaction Research and Applications: 9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings (Vol. 3, pp. 403-413). (Communications in Computer and Information Science; Vol. 2836 CCIS). Springer. https://doi.org/10.1007/978-3-032-16454-4_23

Winter, Marcus. / In-Situ Audio Experiences : Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement. Computer-Human Interaction Research and Applications: 9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings. editor / Josef F. Krems ; Hugo Plácido da Silva ; Pietro Cipresso. Vol. 3 Cham : Springer, 2026. pp. 403-413 (Communications in Computer and Information Science).

@inproceedings{8dd5f6e02935404896917998c82b0612,

title = "In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement",

abstract = "This position paper presents an application concept adapting Retrieval Aug-mented Generation (RAG) for geographic contexts, and combining it with Text-to-Speech (TTS) technology to automate the creation of audio narrations for locative media experiences. By minimizing the costs for research and me-dia production, it addresses a critical barrier for archives to remediating their content and catering for audiences who are not able to, or not inclined to, read written materials. The application concept is contextualized in efforts to create alternative media representations that convey content in-situ to increase its relevance. It is illustrated with a prototype application aiming to engage peo-ple with their local history through audio narrations fictionalizing archive ma-terials related to their location. A discussion of technical and user interface as-pects offer insights into design considerations informing the prototype devel-opment.",

keywords = "Cultural heritage (CH), Hyperlocal media, Location-based services, Accessibility, Archives, Large language model (LLM), Retrieval Augmented Generation (RAG), Text-to-Speech (TTS)",

author = "Marcus Winter",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 9th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2025) ; Conference date: 20-10-2025 Through 21-10-2025",

year = "2026",

month = feb,

day = "13",

doi = "10.1007/978-3-032-16454-4\_23",

language = "English",

isbn = "9783032164537",

volume = "3",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "403--413",

editor = "Krems, \{Josef F.\} and \{da Silva\}, \{Hugo Pl{\'a}cido\} and Pietro Cipresso",

booktitle = "Computer-Human Interaction Research and Applications",

url = "https://chira.scitevents.org/",

}

Winter, M 2026, In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement. in JF Krems, HP da Silva & P Cipresso (eds), Computer-Human Interaction Research and Applications: 9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings. vol. 3, Communications in Computer and Information Science, vol. 2836 CCIS, Springer, Cham, pp. 403-413, 9th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2025), Marbella, Spain, 20/10/25. https://doi.org/10.1007/978-3-032-16454-4_23

In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement. / Winter, Marcus.
Computer-Human Interaction Research and Applications: 9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings. ed. / Josef F. Krems; Hugo Plácido da Silva; Pietro Cipresso. Vol. 3 Cham: Springer, 2026. p. 403-413 (Communications in Computer and Information Science; Vol. 2836 CCIS).

Research output: Chapter in Book/Conference proceeding with ISSN or ISBN › Conference contribution with ISSN or ISBN › peer-review

TY - GEN

T1 - In-Situ Audio Experiences

T2 - 9th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2025)

AU - Winter, Marcus

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026/2/13

Y1 - 2026/2/13

N2 - This position paper presents an application concept adapting Retrieval Aug-mented Generation (RAG) for geographic contexts, and combining it with Text-to-Speech (TTS) technology to automate the creation of audio narrations for locative media experiences. By minimizing the costs for research and me-dia production, it addresses a critical barrier for archives to remediating their content and catering for audiences who are not able to, or not inclined to, read written materials. The application concept is contextualized in efforts to create alternative media representations that convey content in-situ to increase its relevance. It is illustrated with a prototype application aiming to engage peo-ple with their local history through audio narrations fictionalizing archive ma-terials related to their location. A discussion of technical and user interface as-pects offer insights into design considerations informing the prototype devel-opment.

AB - This position paper presents an application concept adapting Retrieval Aug-mented Generation (RAG) for geographic contexts, and combining it with Text-to-Speech (TTS) technology to automate the creation of audio narrations for locative media experiences. By minimizing the costs for research and me-dia production, it addresses a critical barrier for archives to remediating their content and catering for audiences who are not able to, or not inclined to, read written materials. The application concept is contextualized in efforts to create alternative media representations that convey content in-situ to increase its relevance. It is illustrated with a prototype application aiming to engage peo-ple with their local history through audio narrations fictionalizing archive ma-terials related to their location. A discussion of technical and user interface as-pects offer insights into design considerations informing the prototype devel-opment.

KW - Cultural heritage (CH)

KW - Hyperlocal media

KW - Location-based services

KW - Accessibility

KW - Archives

KW - Large language model (LLM)

KW - Retrieval Augmented Generation (RAG)

KW - Text-to-Speech (TTS)

UR - https://www.scopus.com/pages/publications/105030657571

U2 - 10.1007/978-3-032-16454-4_23

DO - 10.1007/978-3-032-16454-4_23

M3 - Conference contribution with ISSN or ISBN

SN - 9783032164537

VL - 3

T3 - Communications in Computer and Information Science

SP - 403

EP - 413

BT - Computer-Human Interaction Research and Applications

A2 - Krems, Josef F.

A2 - da Silva, Hugo Plácido

A2 - Cipresso, Pietro

PB - Springer

CY - Cham

Y2 - 20 October 2025 through 21 October 2025

ER -

Winter M. In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement. In Krems JF, da Silva HP, Cipresso P, editors, Computer-Human Interaction Research and Applications: 9th International Conference, CHIRA 2025, Marbella, Spain, October 20–21, 2025, Proceedings. Vol. 3. Cham: Springer. 2026. p. 403-413. (Communications in Computer and Information Science). doi: 10.1007/978-3-032-16454-4_23

In-Situ Audio Experiences: Leveraging RAG and TTS for Accessible, Hyperlocal Heritage Engagement

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this