Design and Implementation of an ESP32-Based Turkish Voice Assistant Using Locally Hosted Artificial Intelligence Models
This work presents the design and implementation of a Turkish-speaking voice assistant based on the ESP32 microcontroller and locally hosted artificial intelligence models. The system integrates Faster-Whisper for speech recognition, Llama 3.2 through Ollama for response generation, and eSpeak NG for speech synthesis. Audio communication between the ESP32 and a local computer is implemented using Wi-Fi and WebSocket. The document describes the hardware architecture, software implementation, communication protocol, and evaluation methodology. Illustrative simulated performance data are explicitly identified as simulations and should not be interpreted as measured hardware results.
Authors
- Ömer Gürgen (ORCID: https://orcid.org/0009-0001-5593-3081)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24336040
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00