siim

Speaking > typing for creation.

Reading > listening for consumption.

Talk to create, read to consume.

Curious what made you think the backend uses LLMs for content generation?

To clarify:

1. transcription is local VOSK speech-to-text via WebSocket

2. live transcript post-processing has optional Gemini Flash-lite turned on which tries to fix obvious transcription mistakes, nothing else. The real fix here is more accurate transcriber.

3. backend: TypeGraphQL + MongoDB + Redis

The anti-AI stance isn't "zero AI anywhere", it's about requiring human input.

AI-generated audio is either too bad or too perfect. Real recorded voice has human imperfections.

That's a good call. While there's no general public feed, individual profiles are public. For example, here's mine: https://voxconvo.com/siim

True. However making voice input has higher friction than typing chatgpt write me a reply.

I'm working on https://X11.Social, a voice-first content creation tool for X.

The initial idea was "call to tweet", the ability to compose posts on the go by having a natural conversation with an AI assistant over a simple phone call. This is useful for turning thoughts from a walk or drive into a polished "brain dump" post, or for engaging with user lists without being at a computer.

It has since evolved into a broader system:

Chrome Extension: A context-aware assistant that lives in the browser. It has a Quake-style console (activated by opt+space) for quick chat and can analyze the content of any page you're on (e.g., YouTube transcripts, articles, other tweets) to help you create relevant content.

Engagement Predictor: A feature that scores tweet drafts in real-time to predict their potential for engagement. It's built on a model trained on my own dataset pulled from the X API and other public dataset from Kaggle[0].

Scheduled AI Calls: The system can call you on a predefined schedule to proactively brainstorm content ideas.

Here is the tech stack:

- Frontend: React, Tailwind, shadcn/ui

- Auth: X OAuth

- Payments: Stripe Subscriptions

- Voice AI: ElevenLabs Conversational AI, Twilio

- Engagement Predictor ML: Python, scikit-learn, XGBoost on a data pipeline from X API v2 and a base dataset from Kaggle.

- Chrome Extension: Same as Frontend and Chrome Extensions API

- Blog: Jekyll

- Infrastructure: Deployed on AWS Fargate using AWS Copilot for orchestration (ECS).

I'm building solo and just got the first trial user after 87 days of building in public. It's a long road but the feedback so far is encouraging.

[0] https://www.kaggle.com/code/shpatrickguo/tweet-virality-pred...

Fair. X11 is ElevenLabs-inspired voice tech, X for the platform + 11 for AI voice.

I kept the name for the call-to-tweet vision. Thoughts on the demo?

After looking into to the code I found out that this app is made by using Voronoi diagrams. [1]

The actual positions are saved in a json file. [2]

[1] http://en.wikipedia.org/wiki/Voronoi_diagram

[2]http://www.pointerpointer.com/gridPositions.json

Edicy is a nice CMS solution with in-line editing. http://www.edicy.com/

I found a quick 15 page introduction to Scala and took me about an hour to digest it (of course I didn't dive in very deeply). It gave me a sufficient knowledge to understand the article about monads.

So here it is: http://www.scala-lang.org/docu/files/ScalaTutorial.pdf

This latching and piping seems intuitive if you have done some monadic programming in Haskell.

I recently discovered, that I can hide Opera's tab bar and use panels 'Windows' panel instead (easy to toggle with F4).

This reminds me of that south park episode with underpants gnomes:

  1) Collect underpants
  2) ?
  3) Profit

http://onstartups.com/tabid/3339/bid/8608/Startup-Lessons-Fr...