Creator builds full motion graphic poem end-to-end with Gemini 3.1 TTS and Lyria
aziz4ai · x · 2026-09-18
A Saudi creator showed off a motion-graphic piece about Saudi Arabia made entirely inside an AI model: a metric Arabic poem, images from official sources, plus voiceover and music. He was especially impressed by Gemini 3.1 TTS's delivery — paired with Google's Lyria music generation, "the words hit hard." A demonstration of end-to-end content creation with a multimodal tool stack.
More from Fun
- Dev turns physical Pokémon cards into playable AR game with Astra + CLAD, all 151 mons — willeastcott · 2026-09-19
- Recalling Coxon in 2022: a trader who later did pretraining, not a safety ideologue — NathanpmYoung · 2026-09-19
- Fully AI-Generated 'Slop Actress' Tilly Norwood Glitches, Speaks Chinese Mid-Interview — Polymarket · 2026-09-19
- Anthropic gives Claude a wet lab, mocked for picking the most perilous path — georgejrjrjr · 2026-09-19
- Codex quietly ate 100GB of a dev's MacBook storage — burkov · 2026-09-19
- Google engineer rakyll: 'I just kubectl applied this manifest and it worked' — rakyll · 2026-09-19