Open Overpass Turbo and load the map + query editor workspace
Data & Research
Validated
Query Geographic Data with Overpass Turbo
Find hospitals, EV charging stations, and schools in any city using plain English queries, then export as GeoJSON.
16 steps
overpass-turbo.eu
demo_overpass.py
0 warnings
Watch The Demo
Open raw assetThis page pairs the final video with publishable screenshots and the exact rerun recipe.
Prompt
Go to overpass-turbo.eu, find all hospitals in Hyderabad, view on map, query EV charging stations, export as GeoJSON
Reproduce It
python run_all.py --demo overpass_turbo --record python run_all.py --demo overpass_turbo --narrate python run_all.py --demo overpass_turbo --process python run_all.py --demo overpass_turbo --record --narrate --process python run_all.py --page-only
Toolchain
Playwright browser automation
StepLogger captions and screenshots
Gemini TTS with gTTS fallback
FFmpeg compression and caption burn
Artifacts
output/overpass_turbo_final.webmoutput/overpass_turbo_transcript.mdoutput/overpass_turbo_narration.txtoutput/overpass_turbo_narration_timeline.jsonscreenshots/overpass_turbo_steps.jsonoutput/overpass_turbo_manifest.jsontutorials/overpass_turbo.html
Storyboard Slideshow
Slide through each screenshot one step at a time, with the image on top and the step content below.
Storyboard Slideshow:
one step per slide with the screenshot on top and the step content below.
Slide 1 of 16
Split view: query editor on left, map + controls on right
Write a Hyderabad hospitals query in Overpass QL using a fixed city bounding box
Run query to load all mapped hospitals as explorable markers
Use 'zoom to data' to jump map viewport directly onto Hyderabad results
Click map markers to inspect feature tags like name, address, and amenity type
Open Data tab to inspect raw tabular output and OSM attributes
Switch back to Map view to visually compare coverage across neighborhoods
Replace with EV charging station query to analyze clean-mobility readiness
EV charging points rendered; now compare spread versus healthcare locations
Run school query to map education infrastructure in the same city boundary
Add pharmacy query as a fourth dataset to build a richer city-services comparison
Single editor workflow lets you iterate quickly across multiple urban datasets
Open Export options for downstream GIS and analytics workflows
Export supports GeoJSON, KML, GPX, and raw OSM for different tools
Tutorial complete: from iterative query editing to exportable, reproducible geo-data
Final Narration
The exact narration used in the finished audio.
Step 1
Step 1: Open Overpass Turbo and load the map + query editor workspace Map nodes take a second. More math than high school. Boom, rendered.
Step 2
Step 2: Split view: query editor on left, map + controls on right
Step 3
Step 3: Write a Hyderabad hospitals query in Overpass QL using a fixed city bounding box
Step 4
Step 4: Run query to load all mapped hospitals as explorable markers The API is hauling hospital markers worldwide. Fast fiber beats virtue.
Step 5
Step 5: Use 'zoom to data' to jump map viewport directly onto Hyderabad results
Step 6
Step 6: Click map markers to inspect feature tags like name, address, and amenity type
Step 7
Step 7: Open Data tab to inspect raw tabular output and OSM attributes
Step 8
Step 8: Switch back to Map view to visually compare coverage across neighborhoods
Step 9
Step 9: Replace with EV charging station query to analyze clean-mobility readiness Processing again. Come on, little data packets, do your thing.
Step 10
Step 10: EV charging points rendered; now compare spread versus healthcare locations That spread tells you exactly where the future still needs building.
Step 11
Step 11: Run school query to map education infrastructure in the same city boundary Schools are loading. Keep the processors humming. City timelapse, live.
Step 12
Step 12: Add pharmacy query as a fourth dataset to build a richer city-services comparison Final crunch. If the fan is spinning, that is just the sound of progress.
Step 13
Step 13: Single editor workflow lets you iterate quickly across multiple urban datasets One last pass. Look at that density. Pure data art.
Step 14
Step 14: Open Export options for downstream GIS and analytics workflows
Step 15
Step 15: Export supports GeoJSON, KML, GPX, and raw OSM for different tools
Step 16
Step 16: Tutorial complete: from iterative query editing to exportable, reproducible geo-data