Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63145
Volume:
10 |
5 |
May 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
Artificial Intelligence Engineering
Priyadarshini Bhagwati College of Engineering
This document introduces VoicePlot AI, a platform that transforms spoken audio into tangible hand-written output via a CNC pen plotter. The pipeline con-nects four unique stages: capturing audio through sounddevice, transcribing speech to text locally with OpenAI Whisper, generating scalable vector graphics (SVG) using a personalized single-stroke font renderer, and controlling hardware motors via the AxiDraw Python API that operates a custom CNC pen plotter. A web server based on Flask integrates all phases and provides a browser dashboard for live monitoring and management. The system functions completely offline, requiring no in-ternet connection during operation, which makes it appro-priate for use in areas with limited connectivity. Experi-mental testing shows effective end-to-end transcription and physical representation of spoken phrases, achieving a word error rate below 10% for clear speech. The pen-lift servo's hardware characterization showed a cold-start delay, resulting in the initial written word being missed; the underlying issue and a software solution are outlined thoroughly. Possible uses include accessibility tools for individuals with motor disabilities, automated generation of certificates, and AI-based art installations.
KEYWORDS
VoicePlot AI demonstrates that it is now practical to build a voice-to-handwriting system using entirely open-source components running on commodity hardware, with no cloud dependency and an installation that fits in a single batch script. The pipeline from microphone to pen-on-pa-per works reliably for English speech in controlled acous-tic conditions, and the physical output is consistently readable. The main technical contributions are: the description of the end-to-end pipeline integration across four complex subsystems; the identification and software fix of the cus-tom plotter servo cold-start bug; and the implementation of a custom single-stroke font for direct SVG path gener-ation. The servo fix a warmup path plus an increased pen_delay_down value is likely to be relevant to anyone using the AxiDraw API with SG90-based plotter hard-ware. Future work will focus on three areas: Voice Activity De-tection for natural recording without a fixed time win-dow; Devanagari script support for Hindi and Marathi output; and emotion-aware font style selection, where a sentiment analysis layer chooses between different em-bedded fonts based on the detected tone of speech.
[1] R. R. Jegan, S. Sobana, and K. S. Nath, "Modern De-sign and Implementation of XY Plotter," International Journal of Pure and Applied Mathematics, vol. 119, no. 12, pp. 13659–13665, 2018. [2] Y. M. Hasan, A. A. Ali, and M. M. Ahmed, "3-Axes Plotter Machine by Arduino and CNC Shield," Interna-tional Research Journal of Engineering and Technology (IRJET), vol. 05, no. 06, pp. 1234–1239, 2018. [3] A. Pinheiro, B. S. Darsana, and J. George, "Wireless CNC Plotter," International Journal of Advanced Re-search in Electrical, Electronics and Instrumentation En-gineering, vol. 5, no. 5, pp. 45–50, 2016. [4] S. Chamraz, P. Drgona, and M. Hrianka, "Control of Mechatronic Systems Using Integer Arithmetics," in Proc. IEEE 12th Int. Symp. on Applied Machine Intelli-gence and Informatics (SAMI), 2014, pp. 115–118. [5] M. Bhavani, V. S. Kumar, and K. R. Reddy, "Design and Implementation of CNC Router for Engraving," In-ternational Journal of Engineering and Advanced Tech-nology (IJEAT), vol. 8, no. 4, pp. 210–214, 2019. [6] K. J. Madekar, K. J. Nanaware, and P. R. Sonawane, "Automatic Mini-CNC Plotter Machine for PCB Draw-ing," International Journal of Innovative Research in Computer and Communication Engineering, vol. 4, no. 2, pp. 120–125, 2016. [7] U. Pandey, A. Kumar, and S. Singh, "Low-Cost CNC Plotter Using Arduino and L293D Shield," International Journal of Engineering Research & Technology (IJERT), vol. 6, no. 5, pp. 560–564, 2017. [8] S. Ranjan, V. Kumar, and R. Singh, "Low-Cost 2D Plotter Using Arduino and Motor Driver ICs," Journal of Emerging Technologies and Innovative Research (JE-TIR), vol. 8, no. 4, pp. 345–350, 2021. [9] M. Aditi, S. N. Patil, and R. K. Gupta, "Automated Writing and Drawing Machine with Speech Recogni-tion," in Proc. Int. Conf. on Smart Electronics and Com-munication (ICOSEC), 2021, pp. 789–794. [10] A. V. Satikosre, P. D. Patil, and S. R. Deshmukh, "Automatic Writing Machine for Handwriting Replica-tion," International Journal of Scientific Research in Sci-ence and Technology (IJSRST), vol. 9, no. 3, pp. 112–118, 2022.
Publication Date
5/13/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...