---
title: "Slides: How to talk to statues — Joe Reeve, ElevenLabs"
category: "slides"
video_id: "u-rJwPPU3QA"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: How to talk to statues — Joe Reeve, ElevenLabs

## Source Video
[How to talk to statues — Joe Reeve, ElevenLabs](https://www.youtube.com/watch?v=u-rJwPPU3QA)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/u-rJwPPU3QA/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/u-rJwPPU3QA/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: advanced OCR `rapidocr-live/full`.
- OCR decision: ready — Dense multi-panel product slide with many small labels and screenshots.

Slide text:

> Generate Speech Convert text to speech wh themost any platform. Transcribe Speech Reattme or batch Speech to Text for Compose Music Generate stems,yrics,and fl compositions with fult flexibility
> Ughit of e Night
> AIE cy emeet yo.on Dhe enemy of iogkc.
> Create Sound Effects Seamless looping, any length, professional-grade sound effects. Clone someone's voice,generate one existing 10k voices. with a prompt,or use one ofour Create Voices Deploy Agents Fully managed agents platform, with Nastive SDKs for mobile and web.
> Space sni
> tsEL4543490
> Engineering the future of Al
> AIEng

![[assets/slides/u-rJwPPU3QA/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/u-rJwPPU3QA/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.93`
- Text source: advanced OCR `rapidocr-live/full`.
- OCR decision: ready — Embedded screenshots and dense small text are better suited for OCR than manual transcription in this pass.

Slide text:

> Whosawthis?
> Over1.5m impressions
> R The British MuseumLondon,United Kingdom ArtemistheHuntress(Romanmarbl.
> Identit Research
> AIE can ust do stulr / buld in publc Unknown Roman sculptor,after a Greek original ARTIST
> YEAR Roman Imperial period,roughly st-2nd century AD
> SIMPLYUSETHAT
> 10.30 AM-F40 19, 2026 44mK Vow information.
> httos://x.com/isnit0/status/20244314992 65585249
> AIEngineer
> EUROPE
> AIEng

![[assets/slides/u-rJwPPU3QA/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/u-rJwPPU3QA/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.94`
- Text source: agent_vision.
- OCR decision: ready — Contains several dense webpage screenshots and small interface text that OCR will capture better than manual reading.

Slide text:

> Build. Ship. Win.


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/u-rJwPPU3QA/slide-001.jpg) — `speaker_stage` confidence `0.98`; Camera shot of speaker and audience with a projector screen; not a presentation slide frame.
- [`slide-004.jpg`](/assets/slides/u-rJwPPU3QA/slide-004.jpg) — `speaker_stage` confidence `0.99`; Speaker photo/intro frame on a black background; no meaningful slide content.
- [`slide-006.jpg`](/assets/slides/u-rJwPPU3QA/slide-006.jpg) — `title_card` confidence `0.97`; Branding-only closing card with logo and URL, not substantive presentation content.

Classification audit: `raw/sources/slide-ai-classification/slides/u-rJwPPU3QA/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.