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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Design and Implementation of an ESP32-Based Turkish Voice Assistant Using Locally Hosted Artificial Intelligence Models

Ömer Gürgen
2 links
Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
article

Design and Implementation of an ESP32-Based Turkish Voice Assistant Using Locally Hosted Artificial Intelligence Models

Ömer Gürgen
article en

Abstract

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.

Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon