Skip to content

emhgit/pdf-voice-assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

93 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PDF Voice Assistant

A web application that allows users to fill out PDF forms by speaking. The app captures the user’s voice, transcribes it to text, uses a local language model (e.g. Mistral via Ollama) to extract structured data, maps that data to the form fields of a PDF, and returns the filled-out document. It dynamically supports any fillable PDF and adapts to multiple or non-standard fields based on user input.

Tech Stack:

● Frontend: Vite, React, React Router DOM, TypeScript, TailwindCSS, MicRecorder, File upload

● Backend: Node.js (Express), FastAPI Python microservices (Whisper) and Ollama (Mistral) ● Libraries: pdf-lib, fs, multer.js, ollama

(WIP)

About

Web application that allows users to fill out PDF forms by speaking

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published