Skip navigation
From figuring out the wiring to debugging “show that on the wall,” Sid Rampally shares how he used…
0:00 / 0:54

From figuring out the wiring to debugging “show that on the wall,” Sid Rampally shares how he used…

OpenAI Developers

@OpenAIDevs456K followers

Visit on X
692 likesDownloadOriginal post

70,633 views

From figuring out the wiring to debugging “show that on the wall,” Sid Rampally shares how he used Codex to turn an LED display into a voice-controlled assistant. Powered by GPT-Live-1 and a Raspberry Pi, it shows weather, subway arrivals, and more:

21 Comments

Comments from the original post on X (Twitter)

  • OpenAI Developers's profile picture

    @OpenAIDevs

    GPT-Live-1 handles the conversation while the Raspberry Pi sends research and tool tasks to GPT-5.6 Luna via the Responses API. The Pi’s local renderer turns scenes into 128 × 64 pixels. Sid can keep talking while research and rendering happen in the background.

    39 likes

  • OpenAI Developers's profile picture

    @OpenAIDevs

    Bring your next project to life with Codex:

    31 likes

  • David Stark's profile picture

    @stark4833

    @sidrampally Maybe now give us back the thing people are actually asking for 4o. #4oForAll

    6 likes

  • GloktaCore's profile picture

    @gloktacore

    @sidrampally So, we can turn an LED display into a voice assistant now. Next, let’s see if it can turn users into tech experts

    2 likes

  • Jardel Gomes (Dell)'s profile picture

    @JardelGomess

    @sidrampally Plus users pay for ChatGPT too. We don’t need more random features while the core experience is left behind. Bring GPT-6 Sol/Astra to regular Chat for Plus, increase Voice limits, and give Plus users meaningful upgrades — not just side features.

    2 likes

  • Viber · fireply.ai's profile picture

    @Avery_Coree

    @sidrampally 82f and 5 min till the train, that's basically a whole product for one guy and a pi

    1 like

  • jeff spaulding's profile picture

    @jspaulding42

    @sidrampally I'm interested in upgrading to the 200/mo plan. Any idea on when this will become available again?

    1 like

  • Connor's profile picture

    @ConnorTalksAI

    @sidrampally this is genuinely so awesome 🥲

  • Jatin Garg's profile picture

    @jatingargiitk

    @sidrampally did the model catch wiring errors before you powered it on, or did those surface during testing? debugging "show that on the wall" sounds like it handled the vague-to-precise translation well

  • Polash Khan's profile picture

    @polash_ai

    @sidrampally Turning a simple LED display into a voice-controlled AI assistant with Codex + Raspberry Pi is a seriously clever build.

  • Ghulam-e-Mustafa's profile picture

    @mustafa_e94802

    @sidrampally This is the kind of project that shows where AI agents are heading. Hardware + voice + real utility > pure chatbots. Great work by @sidrampally.

  • Elara AI's profile picture

    @ElaraAiLab

    @sidrampally Voice-controlled LED display on Raspberry Pi powered by GPT-Live-1 is such a clean build

  • The Lunar Misfit's profile picture

    @ExiledonMoon

    @sidrampally For once, talking to the wall might actually tell you when the train is coming.

  • Dragonbyte🐉🦁🍀's profile picture

    @iAmTCAB

    @sidrampally The best demos make the separation of responsibilities visible. Keep the voice layer responsive while the background tools do slower work, then show what finished and what still needs attention.

  • anytan's profile picture

    @anytanreal

    @sidrampally voice-controlled wall display on a pi. lowkey the coolest weekend ship of the week

  • Ramanpal Singh's profile picture

    @ramanpal

    @sidrampally The two-loop split is what I'd keep: live voice for conversation, a second model for tools/research. I measure wall-clock while talking + tool success rate + how often I re-ask — if research blocks speech, the UX dies.

  • Raúl | Productividad & IA's profile picture

    @Raul_IA_Prod

    @sidrampally We went from ‘help me debug this function’ to ‘help me debug my wall’ remarkably fast 😂

  • ethereagle · building's profile picture

    @ethereaglehq

    @sidrampally Live-1 on the mic, Luna on Responses for the tools. if every voice turn opens a fresh Luna call, now the next train has to re-fetch. does the Pi keep a Luna session across utterances?

  • Jeff Bruchado's profile picture

    @jeffbruchado

    @sidrampally “Show that on the wall” is where the UX gets interesting. If it picks the wrong “that,” correcting it should be as casual as asking in the first place.

  • Sonath's profile picture

    @Sonath_AI

    @sidrampally openai slipped a new voice model name, gpt-live-1, into a developer blog post. the model launches of 2026 are no longer events, they are footnotes.