Install Wispr Flow
Pick your agent. Every command is ready to paste.
npx skills add ArtemXTech/personal-os-skills --skill wispr-flowThe open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.
01
Install it
Run the command above, or upload the folder in Claude.
02
Ask naturally
Describe the task. Your agent loads wispr-flow when the request matches its description.
03
Name it if needed
If it does not trigger, say “use the wispr-flow skill”. In Codex, type $wispr-flow.
Wispr Flow Skill
Access and analyze your Wispr Flow voice dictation history.
Quick Stats
# Overall stats
{baseDir}/scripts/get-stats.py
# Today only
{baseDir}/scripts/get-stats.py --period today
# This week
{baseDir}/scripts/get-stats.py --period week
# JSON output
{baseDir}/scripts/get-stats.py --json
Search
# Search all dictations
{baseDir}/scripts/search-history.py "keyword"
# Filter by app
{baseDir}/scripts/search-history.py "keyword" --app ghostty
# Date range
{baseDir}/scripts/search-history.py "keyword" --from 2026-01-01 --to 2026-01-10
Export
# JSON backup (text only, portable)
{baseDir}/scripts/export-data.py -o ~/Downloads/wispr-backup.json
# Obsidian daily notes format
{baseDir}/scripts/export-data.py --format obsidian -o ~/vault/Voice/
Visualization
# Generate interactive HTML dashboard
{baseDir}/scripts/create-dashboard.py -o ~/Downloads/wispr-dashboard.html
open ~/Downloads/wispr-dashboard.html
Quick Queries (Direct SQL)
# Recent dictations (EST timezone)
sqlite3 ~/Library/Application\ Support/Wispr\ Flow/flow.sqlite "
SELECT datetime(timestamp, '-5 hours') as time, app, substr(formattedText, 1, 80)
FROM History ORDER BY timestamp DESC LIMIT 10
"
# Words by app
sqlite3 ~/Library/Application\ Support/Wispr\ Flow/flow.sqlite "
SELECT app, SUM(numWords) as words FROM History
WHERE app IS NOT NULL GROUP BY app ORDER BY words DESC LIMIT 10
"
# Today's word count
sqlite3 ~/Library/Application\ Support/Wispr\ Flow/flow.sqlite "
SELECT SUM(numWords) FROM History
WHERE date(timestamp, '-5 hours') = date('now', '-5 hours')
"
Database
Location: ~/Library/Application Support/Wispr Flow/flow.sqlite
Key tables:
History- all dictations (timestamp, app, formattedText, numWords, duration, audio blob)
Timezone: Database stores UTC. Use -5 hours for EST.
Space Management
See docs/space-management.md for cleaning up audio blobs.
Troubleshooting
See docs/troubleshooting.md for common issues.
Tips for Wispr Flow
- • Start a fresh session after installing so your agent picks up the new skill.
- • This skill ships scripts. Read them before the first run, and run it in a project without secrets first.
- • It bundles reference files. The agent reads them only when needed, so they cost no context until then.
- • It is part of a pack with 8 skills. Install only the ones you need with --skill to keep triggers precise.
- • If two skills overlap, mention the one you want by name.
Questions about Wispr Flow
What does the Wispr Flow skill do?
Analyze Wispr Flow voice dictation data. Stats, search, export, visualizations. Use when user says "dictation history", "word counts", "voice analytics", "how much did I dictate", "search my dictation".
How do I install Wispr Flow?
Run "npx skills add ArtemXTech/personal-os-skills --skill wispr-flow" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.
Does Wispr Flow work in Cursor and Codex?
Yes. Wispr Flow uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.
Is Wispr Flow free?
Wispr Flow is open source on GitHub under the MIT license. It is free to install; check the license before commercial use.
Who made Wispr Flow?
Wispr Flow is published by ArtemXTech in the ArtemXTech/personal-os-skills repository, together with 7 other skills.





