CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Prompt Engineering for AI Voice Agents: A Practical Guide to Engaging Conversations
Stockholm University of the Arts, Film and Media.ORCID iD: 0000-0001-5878-3157
(English)Manuscript (preprint) (Other academic) [Artistic work]
Abstract [en]

This article presents practical guidelines for prompt engineering in Voice AI agents, with a focus on creating engaging, natural, and adaptive conversational experiences. Drawing from industry practices, community insights, and real-world implementations, it outlines methods for structuring prompts, handling dynamic user inputs, refining tone and persona, and iteratively improving system performance. Special attention is given to applications within the cultural sectors and customer support bots, highlighting how prompt design shapes user experience in voice-first interfaces.

Abstract [sv]

Denna artikel presenterar praktiska riktlinjer för promptdesign i röststyrda AI-agenter, med fokus på att skapa engagerande, naturliga och adaptiva konversationsupplevelser. Med utgångspunkt i branschpraxis, insikter från communityn och verkliga implementeringar, beskrivs metoder för att strukturera prompts, hantera dynamiska användarinmatningar, förfina ton och personlighet samt iterativt förbättra systemets prestanda. Särskild uppmärksamhet ägnas åt tillämpningar inom kultursektorn och kundsupport, med betoning på hur promptdesign påverkar användarupplevelsen i röstbaserade gränssnitt.

Keywords [en]
Automatic speech recognition (ASR), conversational design, conversational interfaces, dialogue systems, human-AI interaction, human-machine interaction, LiveKit, LLMs, multimodal interaction, natural language generation, OpenAI API, prompt engineering, real-time voice processing, realtime AI, rime, speech synthesis, speechmatics, STT, TTS, user experience (UX), voice AI agents
National Category
Natural Language Processing Human Computer Interaction Comparative Language Studies and Linguistics Humanities and the Arts Languages and Literature Comparative Language Studies and Linguistics Computer and Information Sciences Humanities and the Arts Performing Art Studies Performing Arts Ethics Aesthetics
Research subject
Degree of Doctor of Philosophy in Fine Arts in Performative and Media Based Practices with Specialisation in Film and Media.; Artistic practices; Artistic Practices; Konstnärlig doktorsexamen i performativa och mediala praktiker med inriktning i film och media
Identifiers
URN: urn:nbn:se:uniarts:diva-2057OAI: oai:DiVA.org:uniarts-2057DiVA, id: diva2:1946690
Note

Realtime AI

Available from: 2025-03-21 Created: 2025-03-21 Last updated: 2025-04-01Bibliographically approved

Open Access in DiVA

Prompt Engineering for AI Voice agents(454 kB)34 downloads
File information
File name FULLTEXT01.pdfFile size 454 kBChecksum SHA-512
49e28834feb8752eebb7625421ea73a34552f3d578dadc58e216c0ea99793ea66dcb25ff70b023daf94d39cd37eac34a5ff9c858efd649133731e743b69a4ca5
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Johnson, Marc
By organisation
Film and Media
Natural Language ProcessingHuman Computer InteractionComparative Language Studies and LinguisticsHumanities and the ArtsLanguages and LiteratureComparative Language Studies and LinguisticsComputer and Information SciencesHumanities and the ArtsPerforming Art StudiesPerforming ArtsEthicsAesthetics

Search outside of DiVA

GoogleGoogle Scholar
Total: 35 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 74 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf