---
title: "Build realtime multimodal agents with Gemini Live"
category: "talks"
date: "2026-06-30"
time: "10:45am-11:05am"
track: "Workshops Day 2"
room: "Track 4"
speakers: ["Thor 雷神 Schaeff"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Workshops Day 2"
scheduleRoom: "Track 4"
scheduleLabels: ["Workshops Day 2", "Track 4", "session", "confirmed"]
---
# Build realtime multimodal agents with Gemini Live

## Conference Context
- Date/time: 2026-06-30 · 10:45am-11:05am
- Track/room: Workshops Day 2 · Track 4
- Speaker(s): Thor 雷神 Schaeff
- Session type/status: session · confirmed

- Track: Workshops Day 2
- Room: Track 4
- Session type: session
- Status: confirmed

## Session Description
The Gemini Live API is incredible versatile when it comes to building realtime AI experiences. From live translation across 2000 different language pairs to building realtime multimodal agents that can work across text, audio, and vision. This workshop gets you from zero to fully conversational agent in a matter of hours.

## Media Evidence
[From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind](https://www.youtube.com/watch?v=Bc6Ojl2XS1w) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

These are phone-photo slide captures from the Google Photos `AIE Slides` album. They are supporting slide evidence and do not override official schedule fields.
- [[google-photos-aie-slides-9gWZzS1EpXM1C5eK6-gemini-live-slides]] - Google Photos Slides: Gemini Live API Workshop (confidence: medium).

- Source video: `youtube-Bc6Ojl2XS1w`
- Slide deck: [[youtube-Bc6Ojl2XS1w-dense-slides|Dense Slides: From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind]] — 1 visible slide image(s); 1 HTML recreation(s).
![[assets/dense-slides/Bc6Ojl2XS1w/slide-001.jpg]]
- Additional slide evidence: [[youtube-Bc6Ojl2XS1w-slides|Slides: From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind]], [[youtube-Bc6Ojl2XS1w-reconstructed-slides|Reconstructed Slides: From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind]]
- Slide-derived themes for `youtube-Bc6Ojl2XS1w`: engineering, future.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
- `youtube-Bc6Ojl2XS1w` — 1 slide-derived text signals
- Slide-derived themes for `youtube-Bc6Ojl2XS1w`: engineering, future.
- Evidence links for `youtube-Bc6Ojl2XS1w`: [[youtube-Bc6Ojl2XS1w]], [[youtube-Bc6Ojl2XS1w-slides]], [[youtube-Bc6Ojl2XS1w-dense-slides]], [[youtube-Bc6Ojl2XS1w-reconstructed-slides]]

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

## People
- [[thor-schaeff]]

## Supporting Slides
- [[youtube-Bc6Ojl2XS1w-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-Bc6Ojl2XS1w-dense-slides]] (1 viable slide images).
- Related slide/OCR pages:
- [[youtube-Bc6Ojl2XS1w-dense-slides]]
- [[youtube-Bc6Ojl2XS1w-reconstructed-slides]]
- [[youtube-Bc6Ojl2XS1w-slides]]
- Slide-derived terms: `audio`, `engineer`, `engineering`, `future`, `deepmind`, `gemini`, `performance`, `google`, `thor`, `transcription`, `english`, `transcript`, `prompt`, `speaker`, `context`, `segment`, `following`, `europe`

## Synthesis
### Synthesized Breakdown
# Build realtime multimodal agents with Gemini Live ## Conference Context - Date/time: 2026-06-30 · 10:45am-11:05am - Track/room: Workshops Day 2 · Track 4 - Speaker(s): Thor 雷神 Schaeff - Session type/status: session · confirmed - Track: Workshops Day 2 - Room: Track 4 - Session type: session - Status: confirmed ## Session Description The Gemini Live API is incredible versatile when it comes to building realtime AI experiences. From live translation across 2000 different language pairs to building realtime multimodal agents that can work across text, audio, and vision. This workshop gets you from zero to fully conversational agent in a matter of hours. ## Media Evidence [From Transcription to Live Music: Gemini's Audio Stack — Thor Schaeff, Google DeepMind](https://www.youtube.com/watch?v=Bc6Ojl2XS1w) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

### Speaker And Company Context
- [[thor-schaeff|Thor 雷神 Schaeff]] — Member of the Technical Staff (DevX) at Google DeepMind at [[google-deepmind|Google DeepMind]].

### Topics Covered
- Topic links are pending transcript-backed classification.

### Derived Links And Source Material
- [[youtube-Bc6Ojl2XS1w]] — related YouTube source page.
- [[youtube-Bc6Ojl2XS1w-slides]] — slide evidence.
- [[youtube-Bc6Ojl2XS1w-reconstructed-slides]] — slide evidence.
- [[youtube-Bc6Ojl2XS1w-dense-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.