This paper presents an experience report on the development and pre-testing of a voice-based agentic workflow that uses two large language models, OpenAI’s GPT-4o-mini and the open-source Gemma3:27b to conduct requirement elicitation discussions in a software projects. The growing use of independent AI agents for specialized tasks has motivated our exploration of voice agents as “requirement elicitors” within software projects. The paper describes the approaches attempted during development, including those that were successful and those that failed, along with insights gathered from implementing and testing the use cases. We conducted a pre test round with five participants comparing the two agents’ performance under two case studies. The OpenAI-based agent showed a higher requirements coverage, identifying 77.5 of relevant requirements on average, while the Gemma-based agent captured 35.0. In terms of the usability, participants rated the OpenAI agent 4.0/5, compared to 3.3/5 for the Gemma agent, highlighting more natural conversational flow, contextual understanding, and responsiveness. We propose deploying this voice agent to support requirement elicitation sessions alongside a requirement engineer, serving as the first agent in an extended multi-agent requirements engineering workflow, which will be the extension of this work. The methods, design choices, and lessons learned documented in this report aim to guide practitioners and researchers in adapting similar agent-based approaches in their own domains.