AgoraAI: An Open-Source Voice-to-Voice Framework for Multi-Persona and Multi-Human Interaction
Source abstract
Abstract
This article presents AgoraAI, an open-source framework designed to enable dynamic, multi-participant conversations by integrating Multi-Persona Orchestration within a shared conversational environment. Unlike traditional single-agent Large Language Model (LLM) interactions or passive commercial meeting assistants, AgoraAI allows users to configure distinct AI personas that engage in active facilitation and simultaneous, turn-based dialogues with human participants. The system supports diverse high-stakes use cases, including formal panel discussions and interactive educational settings. Crucially, this work addresses the engineering challenge of the “Concurrency-Coherence Paradox” in real-time voice systems. Key architectural contributions include: (1) the implementation of Asynchronous Dual-Queue Processing, a thread-safe integration strategy that synchronizes real-time Speech-to-Text streams with LLM generation to resolve race conditions; and (2) Dynamic Context-Injection pipelines that ensure persona consistency. The platform’s ecological validity is demonstrated through deployment in a human-supervised Master’s thesis seminar and a corporate coordination meeting. Results from an exploratory pilot study indicate high usability, perceived utility, and strong user acceptance. These findings suggest that AgoraAI provides a flexible, empirically evaluated architecture for democratizing multi-perspective collaboration across education, research, and professional domains.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Persona Design and Applications · AI in Service Interactions · Social Robot Interaction and HRI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Facultad de Ingeniería Mecánica y Eléctrica, Universidad de Colima, Coquimatlán 28400, Colima, Mexico
Departamento de Investigación y Desarrollo, Industria Sigrama S.A de C.V., Torreón 27020, Coahuila, Mexico
Facultad de Ingeniería Mecánica y Eléctrica, Universidad Autónoma de Coahuila, Torreón 27276, Coahuila, Mexico
Funding
Secretaría de Ciencia, Humanidades, Tecnología e Innovación · Programa para el Desarrollo Profesional Docente
References (35)
Show source-provided references
1. Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., and Brunskill, E. (2022). On the Opportunities and Risks of Foundation Models. arXiv.
2. Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N.V., Wiest, O., and Zhang, X. (2024). Large language model based multi-agents: A survey of progress and challenges. arXiv.
3. A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges10.1007/s44336-024-00009-2 ↗
4. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). GPT-4 technical report. arXiv.
5. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., and Azhar, F. (2023). Llama: Open and efficient foundation language models. arXiv.
6. ChatGPT outperforms crowd workers for text-annotation tasks10.1073/pnas.2305016120 ↗
7. Chen, P.Y., and Liu, S. (2025). Introduction to Foundation Models, Springer Nature.10.1007/978-3-031-76770-8 ↗
8. SkyEyeGPT: Unifying remote sensing vision-language tasks via instruction tuning with large language model10.1016/j.isprsjprs.2025.01.020 ↗
9. UPTM-LLM: Large language models-powered urban pedestrian travel modes recognition for intelligent transportation system10.1016/j.asoc.2025.113999 ↗
10. Zhang, D., Li, S., Zhang, X., Zhan, J., Wang, P., Zhou, Y., and Qiu, X. (2023). SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities. arXiv.10.18653/v1/2023.findings-emnlp.1055 ↗
11. Contrive the chat & voice bot based on personal automation through artificial intelligence10.1063/5.0248596 ↗
12. Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., and Sutskever, I. (2022). Whisper: Robust speech recognition via large-scale weak supervision. arXiv.
13. Palbou, L. (2025, October 26). VoiceLLM: A Modular Python Library for Voice Interactions with AI Systems. Available online: https://github.com/lpalbou/VoiceLLM.
14. Lee, O., and Joseph, K. (2025). A large-scale analysis of public-facing, community-built chatbots on Character.AI. arXiv.
15. Voice in human–agent interaction: A survey10.1145/3386867 ↗
16. Park, J.S., O’Brien, J., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (November, January 29). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, San Francisco, CA, USA.
17. de Aquino e Aquino, G., da Silva de Azevedo, N., Okimoto, L.Y.S., Camelo, L.Y.S., de Souza Bragança, H.L., Fernandes, R., Printes, A., Cardoso, F., Gomes, R., and Torné, I.G. (2025). From RAG to Multi-Agent Systems: A Survey of Modern Approaches in LLM Development. Preprints, 2025020406.10.20944/preprints202502.0406.v1 ↗
18. Cox, S.R. (2023). The use of multiple conversational agent interlocutors in learning. arXiv.
19. Taulli, T., and Deshmukh, G. (2025). CrewAI. Building Generative AI Agents: Using LangGraph, AutoGen, and CrewAI, Apress.10.1007/979-8-8688-1134-0 ↗
20. Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., and Cong, X. (2023). Chatdev: Communicative agents for software development. arXiv.10.18653/v1/2024.acl-long.810 ↗
21. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., and Liu, J. (2024, January 7–9). Autogen: Enabling next-gen LLM applications via multi-agent conversations. Proceedings of the First Conference on Language Modeling, Philadelphia, PA, USA.
22. Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Wang, J., Zhang, C., Wang, Z., Yau, S.K.S., and Lin, Z. (2024, January 7–11). MetaGPT: Meta programming for a multi-agent collaborative framework. Proceedings of the Twelfth International Conference on Learning Representations, Vienna, Austria.
23. Wu, Y., Jiang, Z., Khan, A., Fu, Y., Ruis, L., Grefenstette, E., and Rocktäschel, T. (2025, October 26). ChatArena: Multi-Agent Language Game Environments for Large Language Models. GitHub repository, Farama-Foundation/Chatarena. Available online: https://github.com/Farama-Foundation/ChatArena.
24. Al-Onaizan, Y., Bansal, M., and Chen, Y.N. (2024). MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA, 12–16 November 2024, Association for Computational Linguistics.
25. Tran, K.T., Dao, D., Nguyen, M.D., Pham, Q.V., O’Sullivan, B., and Nguyen, H.D. (2025). Multi-agent collaboration mechanisms: A survey of llms. arXiv.
26. Turn-taking in conversational systems and human-robot interaction: A review10.1016/j.csl.2020.101178 ↗
27. Spoken language interaction with robots: Research issues and recommendations10.1016/j.csl.2021.101255 ↗
28. A multi-agent collaborative algorithm for task-oriented dialogue systems10.1007/s13042-024-02374-2 ↗
29. Guo, X., Huang, K., Liu, J., Fan, W., Vélez, N., Wu, Q., Wang, H., Griffiths, T.L., and Wang, M. (2024). Embodied llm agents learn to cooperate in organized teams. arXiv.
30. Bouamor, H., Pino, J., and Bali, K. (2023). Theory of Mind for Multi-Agent Collaboration via Large Language Models. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Singapore, 6–10 December 2023, Association for Computational Linguistics.
31. Kosinski, M. (2023). Theory of mind may have spontaneously emerged in large language models. arXiv.
32. Aleedy, M., Atwell, E., and Meshoul, S. (2025). A Multi-Agent Chatbot Architecture for AI-Driven Language Learning. Appl. Sci., 15.10.3390/app151910634 ↗
33. Gadi, S.K. (2025, December 17). AgoraAI: A Multi-Agent Conversational Framework. Available online: https://github.com/skgadi/agora-ai.
34. Gadi, S.K. (2025, December 17). AgoraAI: Docker Hub Instllation Source. Available online: https://hub.docker.com/r/skgadi/sigrama-agora-ai.
35. Gadi, S.K. (2025, December 17). Real-World Case Studies and Survey Validation of AgoraAI. Available online: https://github.com/skgadi/agora-ai/tree/main/example-events/examples-with-survey.