Open Access Open Access  Restricted Access Subscription Access

AI Voice Assistant Device Using IoT

Mohammed Farhan, Rohit ., Sanjeev Kumar R A, Megha Upase

Abstract


The rapid advancement of Artificial Intelligence (AI) and the Internet of Things (IoT) has enabled the development of intelligent systems capable of human-like communication and between humans and machines through cloud-based APIs, including Google Speech-to-Text (STT), Google Text-to-Speech (TTS), and OpenAI (ChatGPT). The assistant processes user commands, generates intelligent responses, and controls IoT devices via ThingESP integration, while Twilio is used for automated alerts and communication. The device features an I2S-based audio interface for high-quality voice input and output, and operates on rechargeable power for portability. This system demonstrates how low-cost embedded hardware can be transformed into an intelligent assistant capable of real-time speech interaction, smart control, and cloud communication. The results highlight the system’s scalability and potential for applications in smart homes, education, healthcare, and personal assistance.


Full Text:

PDF

References


S. S. Vigneshwar and K. L. Kumar, “AI Voice Assistant Using Python and API,” in Proc. 2024 Int. Conf. on Advances in Data Engineering and Intelligent Computing Systems (ADICS), 2024, doi: 10.1109/ADICS58448.2024.10533536.

M. Subi, M. Rajeswari, J. J. Rajan, and S. Harshini, “AI- Based Desktop VIZ: A Voice-Activated Personal Assistant—Futuristic and Sustainable Technology,” in Facilitating Successful Ageing in Smart Homes,” in Proc. 2023 IEEE Int. Conf. on Pervasive Computing and Communications Workshops (PerCom Workshops), 2023, doi:10.1109/PerCom Workshops 56833.2023.10150259. Proc. 2024 10th Int. Conf. on Communication and Signal Processing (ICCSP),2024,doi:10.1109/ICCSP60870.2024.10543665.

R. Bolimera, K. P. Kumar, R. Sunkuru, P. Mahesh, and

M. Pekkamwar, “AI Enabled Voice Assistant for Visually Impaired,” in Proc. 2024 15th Int. Conf. on Computing Communication and Networking Technologies (ICCCNT), 2024, doi: 10.1109/ICCCNT61001.2024.10724542.

R. Jampala, M. Bhavanam, D. S. Kola, I. R. Pannerselvam, and A. N. Gummadi, “The Evolution of Voice Assistants: From Text-to-Speech to Conversational AI,” in Proc. 2024 2nd Int. Conf. on Intelligent Data Communication Technologies and Internet of Things (IDCIOT), 2024, doi: 10.1109/IDCIOT59759.2024.10467739.

P. Kunekar, A. Deshmukh, A. Bichare, and K. Gunjal, “AI-Based Desktop Voice Assistant,” in Proc. 2023 5th Int. Conf. on Nascent Technologies in Engineering (ICNTE), 2023, doi: 10.1109/ICNTE56631.2023.10146699.

Y. Chen, J. Cai, S. Chen, F. Zulkernine, N. Jaffar, A. Almarzouqi, N. Al-Yateem, and S. A. Rahman, “Assist-Bot: A Voice-Enabled Assistant for Seniors,” in Proc. 2024 IEEE 48th Annual Computers, Software, and Applications Conf. (COMPSAC), 2024, doi: 10.1109/COMPSAC61105.2024.00301.

A. F. Chesser, K. N. Bramlett, A. Atchley, C. E. Gray, and N. L. Tenhundfeld, “Virtual Personal Assistant Design Effects on Memory Encoding,” in Proc. 2022 Systems and Information Engineering Design Symp. (SIEDS), 2022, doi: 10.1109/SIEDS55548.2022.9799387.

M. Al-Kfairy, A. Al-Adaileh, and D. Mustafa, “Building Trust in AI Voice Assistants: Exploring the Role of Security, Information Quality, and Social Influence in the Telecommunications Industry,” in Proc. 2025 16th Int. Conf. on E-Education, E-Business, E-Management and E- Learning (IC4E), 2025, doi: 10.1109/IC4E65071.2025.11075399.

R. Aldhafiri, G. Powell, E. Smith, and C. Perera, “Voice- Enabled Privacy Assistant Towards Facilitating Successful Ageing in Smart Homes,” in Proc. 2023 IEEE Int. Conf. on Pervasive Computing and Communications Workshops (PerCom Workshops), 2023, doi: 10.1109/PerComWorkshops56833.2023.10150259.

M. Shirvanian, S. Vo, and N. Saxena, “Quantifying the Breakability of Voice Assistants,” in Proc. 2019 IEEE Int. Conf. on Pervasive Computing and Communications (PerCom Workshops), 2019, doi: 10.1109/PERCOM.2019.8767399.


Refbacks

  • There are currently no refbacks.