YouTube2Text

Building real-time vision & edge navigation with Gemini Live — Transcript

by Google for Developers · 313 words · 48 segments · language en · Watch on YouTube

Full transcript

  1. 0:01Plants are pretty good at taking care of themselves.
  2. 0:04Until we bring them inside.
  3. 0:10What if a plant could roam to find its own light,
  4. 0:13and ping you when it needs water?
  5. 0:15This is Sprout.
  6. 0:16A plant with a plan.
  7. 0:19We used a TurtleBot 4 for the base,
  8. 0:21a Pixel 11 for the face and eyes,
  9. 0:24and a very real Monstera.
  10. 0:28And Gemini in the background tying it all together.
  11. 0:31We built the software with Gemini,
  12. 0:33in Antigravity.
  13. 0:34That's what's amazing about Gemini
  14. 0:36is the velocity you can get with your project.
  15. 0:38From start to finish, it was about two weeks.
  16. 0:40We wanted it to navigate the office and ID other plants.
  17. 0:43So, Gemini Flash for vision,
  18. 0:45ER 2.0 for segmentation,
  19. 0:48Gemini Live for the voice,
  20. 0:49‘Shall we celebrate with a spin or drive back to check on those plants again?’
  21. 0:53and Nano Banana to sketch what the casing would look like.
  22. 0:56Whether it was on the design, or the fabrication process,
  23. 0:59it was really nice to have like this amazing copilot.
  24. 1:02The base is a TurtleBot,
  25. 1:03basically a Roomba with the chassis,
  26. 1:05a camera, and LiDAR.
  27. 1:07So Sprout can map the room, find the light,
  28. 1:10and dodge whatever's in the way.
  29. 1:12A sensor in the planter, so it knows when it’s thirsty.
  30. 1:15‘Still here! Just making sure my foliage is picture perfect.’
  31. 1:19Then, the satisfying part.
  32. 1:21Putting it all together.
  33. 1:25'Hello, I’m Sprout!’
  34. 1:27Sprout decides by itself
  35. 1:28what should be done in a specific scenario.
  36. 1:31It finds its own light,
  37. 1:33and looks out for its friends.
  38. 1:38And when Sprout needs something,
  39. 1:40it just asks.
  40. 1:42‘I can dance or spin for you now, if you'd like.’
  41. 1:46Tell me a plant joke please.
  42. 1:47‘Why did the gardener plant lightbulbs?
  43. 1:50He wanted to grow power plants!’
  44. 1:52Ah!
  45. 1:53That's good!
  46. 1:54I mean, it's better.
  47. 1:57‘I'm ready for another take
  48. 1:58or a celebratory moonwalk, if you like.’

About this transcript

This page contains the full transcript of Building real-time vision & edge navigation with Gemini Live by Google for Developers, generated from the public captions YouTube serves with the video. The transcript has 313 words across 48 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.