---
title: "Reconstructed Slides: From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind"
category: "slides"
video_id: "Bc6Ojl2XS1w"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind

## Source Video
[From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind](https://www.youtube.com/watch?v=Bc6Ojl2XS1w)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `157.8`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `162.48`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `164.77`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `161.26`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.9`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.02`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.28`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.67`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.47`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `163.79`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `165.09`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `176.05`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.5`
![[assets/reconstructed-slides/Bc6Ojl2XS1w/slide-014.jpg]]

- Source frame: `slide-014.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `160.19`
## Dense Scene-Detected Slide Candidates
- [[youtube-Bc6Ojl2XS1w-dense-slides]]