Open Source CLI • Python & OCR Resume Extraction

Ziara TalentX – Automated Bulk CV Extractor

Parse hundreds of candidate resumes in minutes. Extracts verified candidate phone numbers, emails, and portfolios directly into Excel and CSV.

$git clone https://github.com/Aquil1401/ziara-talentX.git
Documentation →
Recruiting Automation

Stop Copy-Pasting Resumes One By One

Ziara TalentX was engineered for HR departments, hiring managers, and recruitment agencies flooded with hundreds of unformatted job applicant documents.

Point TalentX to a folder containing hundreds of applicant PDFs or Word documents. It scans through every file, performs OCR when necessary, extracts verified contact information, and generates an organized spreadsheet ready for outreach.

Ziara TalentX Logo
Live Terminal Recording

See Ziara TalentX in Action

Watch TalentX bulk parse CVs, run OCR, and extract candidate contacts.

demo.gif — Real execution demo
Ziara TalentX Demo GIF

Features Built for Efficient Recruitment

Say goodbye to manual data entry and focus on hiring the best talent.

Nested Folder Traversal

Recursively scans deeply nested folders of resumes in PDF, DOCX, and image formats in a single command.

Hybrid OCR Engine

Combines text-layer extraction with OCR fallback for scanned or flattened PDF resumes that traditional scrapers miss.

Contact Sanitization

Detects and validates international phone numbers and email formats using regex and heuristic verification.

Export to Excel & CSV

Instantly formats candidate data into structured spreadsheets ready for recruitment CRM import.

Candidate Profile Parsing

Extracts key links including GitHub, LinkedIn, portfolios, and summary skills alongside core contact details.

100% Free & Open-Source

Runs completely locally on your machine. Zero candidate data sent to cloud servers or third-party AI APIs.

Speed Up Candidate Ingestion Today

Free, open-source, and offline-ready. Clone the repo and process your first batch of resumes.