Resume parser
CVs in. Profiles out.
Upload a CV as a PDF, Word file or scan, forward applications by e-mail or send them to the API. Parsevix returns contact details, work history, education, skills and languages as structured data, ready for your applicant tracking system.
- Work history and education, entry by entry
- Skills, languages and certifications as lists
- Personal data masked automatically before the AI step
No credit card · 20 free pages every month
What you get back
Every part of a CV, already defined.
The built-in Resume category returns 36 fields: contact details, the profile, work history, education, languages and lists of certifications, projects, achievements, references and volunteering. Use it as it is, or change it in your project.
Periods and graduation dates come back as the CV writes them, because CVs mix years, months and "today"; dates such as a certification date come back as ISO dates. A field the CV doesn't contain, such as a GitHub profile, is left out, not guessed.
Contact details
personal_infoobject
- full_namestring
- emailstring
- phonestring
- locationstring
- linkedinstring
- githubstring
- websitestring
- date_of_birthdate
- nationalitystring
Profile and skills
- summarystring
- skillsarray
Work history
experiencearray
- companystring
- rolestring
- periodstring
- descriptionstring
Education
educationarray
- institutionstring
- degreestring
- graduation_datestring
- field_of_studystring
- gpastring
Languages
languagesarray
- languagestring
- proficiencystring
Further lists
- certificationsarray
- projectsarray
- achievementsarray
- referencesarray
- volunteerarray
Your own fields
A name, a type and one sentence on what it is.
- notice_period
- salary_expectation
- work_permit
- driving_licence
Made for applications
From a pile of CVs to comparable profiles.
Every applicant writes a CV their own way, in their own layout and often in another language. This is what Parsevix gives you from them.
Candidates side by side
Every CV fills the same fields, so your applicant tracking system can put candidates next to each other: current role, skills and languages in one table, whatever the CVs looked like.
Parsevix extracts what a CV says; it doesn't score, rank or screen candidates. Decisions stay with your team.
- 02
Work history, entry by entry
Each position comes back with its company, role, period and description, in the order the CV lists them.
- 03
Education and certifications
Degrees come back with the institution, field of study and graduation, certifications with their issuer and date.
- 04
Skills as a list
Skills come back as a list of their own, as the CV names them, ready to filter or match in your own system.
- 05
Profiles and links
LinkedIn, GitHub and personal website come back as fields of their own when the CV lists them.
- 06
CVs in any language
The language is detected on every page. A CV in another language fills the same fields, and spoken languages come back with the level the CV gives.
- 07
Names and contacts masked
Names, e-mail addresses, phone numbers and addresses are masked automatically before any text goes to the AI model and put back in your result. Detection catches most personal data, not necessarily every item.
How CVs get in
Upload them, forward them or send them from your system.
Dashboard
Upload CVs as PDFs, Word files or scans. Check each result next to its page, with every value marked where it was printed, and approve it.
E-mail address
Paid plansEvery project gets its own address. Forward applications to it, and each attached CV becomes a document.
API
Send CVs from your careers page or applicant tracking system and get the JSON in the same response, or receive results by signed webhook or through Zapier.
Request
curl https://parsevix.com/api/v1/extract \ -H "X-API-Key: $PARSEVIX_API_KEY" \ -F file=@cv.pdf \ -F category="Resume"
The request stays open until the document is read and answers with the JSON.
- POST /documentsUpload without waiting; the result arrives by webhook or callback.
- POST /extract-autoNo category: every field Parsevix finds, named as in the document.
- POST /classifyOnly the document's category, for 1 credit.
Response · trimmed
Security & compliance
- PII maskedautomatically, before the AI step
- Encryptedin transit and at rest
- No AI trainingon your documents
- API files deletedafter processing
Priced per page, not per feature.
Every plan reads, sorts and masks documents the same way. Picking the category is included, and a document that fails costs nothing.
See pricing- credit per page
- 1
- free pages every month
- 20
- a month for 500 pages
- $39
Resume FAQ
CVs,
answered.
What recruiting teams ask before they send their first CVs.
PDF, Word (DOCX), PNG, JPG and TIFF, up to 10 MB and 30 pages each. Scans work too; every page is read as an image.
No. It extracts what each CV says into fields. It doesn't rate, rank, filter or reject anyone; how you compare candidates and who you invite stays your team's decision.
No. Parsevix reads the text of a CV; a photo is not extracted or described.
You decide what happens to applications; Parsevix processes them for you under the data processing agreement. Names and contact details are masked before any text goes to the AI model, your CVs are never used to train AI, and you can delete a document or a whole project as soon as you no longer need it.
One credit per page: a two-page CV uses two. Choosing the category is included, and if a document fails, its credits are given back.
CVs uploaded in the dashboard or sent by e-mail stay in your project until you delete them. Files sent through the API are deleted after processing unless you turn on keeping them for the project.
Related use cases