Your interviews do not belong in somebody else's cloud

QualiVahti Local

An Obsidian workspace for qualitative research. Keep transcripts, coding decisions, memos, themes, evidence maps, drafts, and the audit trail on your own computer.

Get QualiVahti Local - EUR 49 ONE PAYMENT / LOCAL FILES
QualiVahti Local vault showing a dark file tree, Start Here note, and three human review decisions on model-suggested codes
THE FABRICATED DEMO SHOWS THE WHOLE TRAIL BEFORE YOU ADD YOUR DATA · SWIPE TO INSPECT

Follow one interview all the way through

The vault is organized by analysis stage. Start with audio. End with an interpretation that has a name, a date, and a route back to the material.

01-03

Transcribe and clean

Whisper drafts locally. You correct speakers, names, terms, and keep a cleaning record.

04

Review every code

A local model proposes. You accept, edit, reject, or leave unclear, with a reason beside the row.

05-07

Build interpretation

Stabilize the codebook, memo while reading, define candidate themes, and actively look for negative cases.

08-10

Map and write

Generate evidence maps, matrices, and draft scaffolds that mark where your interpretation goes.

11

Keep the trail

Model and software versions, script runs, review decisions, and theme signatures stay visible.

The real product is the review decision

QualiVahti does not promote a model suggestion into a finding. The researcher has to make the move.

“My life runs in three-month circles, from scan to scan... You live conditionally. Everything gets a little asterisk on it.”

The demo study keeps the raw suggestions next to the review record, including edits, rejections, unresolved rows, and the reasons behind them.

Edited

scan-cycle-life becomes living-scan-to-scanClearer label for the cyclic time experience.

Accepted

conditional-livingParticipant's own logic; the label fits as written.

Rejected

planning-hesitationAlready carried by conditional-living in this excerpt.

No score for “true”A model's confidence is a self-report, so the vault records your reason instead.

What the local models can do. What stays yours.

Models and scripts can

Draft a transcript

You correct the recording against the text.

Suggest first-cycle codes

Each suggestion carries rationale, uncertainty, model, and version.

Propose clusters and counter-readings

A second model can challenge a theme using cited vault material.

Draw tables and evidence maps

Every node remains linked to a note or excerpt.

You remain responsible for

What counts as a code

Accept, revise, reject, or keep the row unresolved.

What the pattern means

Frequency is not importance, and a cluster is not a theme.

What contradicts the claim

Negative cases can narrow, revise, or undo a theme.

What you report

The methods, interpretation, limits, and AI disclosure remain yours.

Inside the vault

The folders arrive in working order, scripts and templates included.

00_Start_Here/

Study dashboard, script guides, citation language, and a map of the workflow.

01_Audio/ - 07_Themes/

The full path from recording through review, codebook, memos, negative cases, and signed themes.

08_Graph_View/ - 12_Exports/

Evidence canvases, methods and results scaffolds, audit records, matrices, tables, and network outputs.

_templates/

Codebook, coding, memo, reflexivity, saturation, theme, conceptual-leap, methods, results, and Canvas templates. The leap note keeps the path from surprise to claim on record: how it works.

_scripts/

Readable Python and R scripts plus local-model prompts. The analysis code is available for citation and supplements.

quickstart.pdf

A visual four-page route through the first hour, review statuses, setup, and the limits of the workspace.

A complete fabricated study ships inside.Three interviews and one focus group move from raw transcript to methods and results scaffolds. No real patient or participant data is included.

What you need

Mac, Windows, or Linux. Obsidian, Python, Ollama, Whisper, and R are free. Setup is documented for researchers who do not normally work in Terminal.

After the initial app and model downloads, the analysis can run without an internet connection. No QualiVahti account is required.

Your computerSensible starting model
8 GB RAMqwen3:4b or llama3.2:3b
16 GB RAMhermes3:8b or qwen3:8b
32 GB or moreqwen3:14b
Disk spaceAllow roughly 10-15 GB for local models

Technical details

The exact formats, scripts, and dependencies, for the researcher, the IT review, or the AI agent evaluating the kit.

format

An Obsidian vault: plain Markdown files plus Canvas boards. Any text editor opens them. No proprietary project database, no export lock-in.

delivery

Zip download through Polar checkout. Version 1.3, 160 files. One personal licence; 1.x updates included.

scripts

12 Python and 9 R scripts, plain readable files: Whisper transcription, transcript cleaning, code suggestion, co-occurrence networks, evidence canvases, participant and theme matrices, frequency and results tables, an AI-disclosure draft, and a preflight check that reports whether review rows, theme signatures, and audit records are in place.

dependencies

Python: faster-whisper and requests, nothing else. R: dplyr, tidyr, readr, ggplot2, igraph, ggraph. Local models run through Ollama's localhost API.

graph RAG

build_vault_graph.py maps the links between your notes; chat_with_vault.py answers questions over that map and cites the notes it read.

prompts

8 local-model prompt files, editable Markdown: first-cycle codes, codebook comparison, theme clusters, negative cases, second-opinion chat, transcription quality check, methods and results drafting.

citation

The analysis scripts are published openly on Zenodo, DOI 10.5281/zenodo.21274892, so your methods section can cite the exact code that ran.

Where QualiVahti stops

It does not find or certify themes.

You interpret, define, challenge, and sign the themes you report.

It does not certify saturation.

Sampling and saturation remain dated research judgments.

Local does not mean risk-free.

Your ethics approval, data-management plan, pseudonymization, and computer security still govern the work.

It does not guarantee correctness or publication.

The workspace makes the path inspectable. It does not make the scientific claim for you.

The method is documented in the open

QualiVahti runs the workflow these free guides teach. Read them before you decide.

Keep the interviews close. Keep the decisions visible.

One personal licence, the complete local vault, and all 1.x updates. Built by Heidi Andersén, MD, PhD.

Get QualiVahti Local - EUR 49

Questions

Does research data touch a server?

The included scripts use local files and localhost to talk to Ollama on your machine. App and model downloads use the internet during setup, without research data. Your own operating-system services and backup settings remain your responsibility.

Does it work with Finnish or Swedish interviews?

Yes. Whisper supports both and the guide explains language selection. You still correct names, specialist terms, dialect, mixed-language speech, and speaker labels against the recording.

Is this an NVivo replacement?

It is a local, file-based workflow for transcription, coding review, codebooks, memos, themes, evidence maps, and reporting. It is not a feature-for-feature clone and does not hide the files in a proprietary project format.

Can a doctoral school or lab use it?

The EUR 49 licence is personal. Lab, teaching, and doctoral-school licences are available from hello@vahtian.com.

Next steps: when the analysis is written up, use the Manuscript Kit, and record what AI you used with the AI Disclosure Kit.