I ve been testing multiple AI voice agent platforms over the last few months.

Almost all of them claim to be no-code but most still require:

We have launched Connecting Odds which is Professionals social networking tool with in built voice call, Video Call, meeting scheduler. I need your support and love to get a good kickstart. We ask everyone to Signup and create their profiles. we are offering founder member badge for the first 500 users. Also we accept the honest feedback from the community.

Every explainer video I tried to make died in the timeline keyframes, re-timing, redo. So I built manic: you write a few plain lines (draw this, move that, flash it green) and it renders a clean animated video. Works for math, algorithms, data structures, and now 3D.

It's for people who don't want to open After Effects teachers, devs writing docs, anyone explaining something visual.
Manic https://8gwifi.org/manic/
Manic Docs http://8gwifi.org/manic/docs

Hi everyone,

I ve been working on FAFI FindAFrameInterpolation, a Windows video player that turns 24, 30, or 60 FPS footage into smooth motion in real time.

FAFI is designed around local playback and privacy:

• Real-time GPU frame interpolation

• Fast MEMC and optional neural RIFE engines

• HDR tone mapping and high-quality upscaling

• Broad video, audio, and subtitle format support

• Built-in accessibility tools

• Optional web video playback

• No ads, accounts, subscriptions, telemetry, or automatic phone-home connections

• Fully offline when playing local files

New plug-in

Hey community! I m pleased to announce our new plug-in Worried Presenter . Worried Presenter listens to you present your work, then gives you back a confident, story-driven script with feedback and tells you exactly how to improve. Here are the steps:

How to use

Giving you a better structure, clearer language, and stronger narrative arc.

Hi Product Hunt I m building AI Voice Wallet, a Telegram-based expense tracker for people who prefer speaking or typing naturally instead of filling out a form. A message like spent 18 AED on lunch and 10 on a cab becomes separate structured records, with summaries and budgets afterward. It does not connect to bank accounts; reports reflect what users record. I d value feedback on whether voice-first entry is useful enough to replace a lightweight manual tracker. Try it: https://t.me/voice_wallet_bot

AI didn't slow your team down. Misalignment and lack of visibility did. AI just exposed it.
We spent the last two years doing agentic engineering work across our own teams and clients. Same thing kept happening: code was moving fast, everything around it wasn't. Docs weeks behind. Tickets missing. Leadership asking what was shipping and getting answers that depended on someone remembering to update the board. Speed up one layer of the system and every gap compounds fast: the more code ships, the less of that speed survives.  We built FlyDocs to close those gaps.
It runs inside your existing AI coding workflow, connecting your editor to Linear or Jira without changing how developers work. You define your team's standards once, and every AI session inherits them. When an agent does the work, it opens the issue, moves it through your workflow, and updates the board on its own. The lead watches the card cross the board in real time while the dev is still in the editor.
We're launching on Product Hunt tomorrow. If you're shipping with AI-assisted development and this sounds familiar, follow us on PH to get notified when we go live: Launch Page
Happy to answer questions in the comments, what part of this breaks down first on your team?

I've been building Fog, a notes app that tries to solve a problem I kept running into: notes apps either make you organize everything manually (folders, tags) or don't organize at all.

Fog uses Apple's on-device Foundation Models framework (the same one powering Apple Intelligence) to read your notes and group related ones into "Clouds" automatically no manual tagging, and nothing ever leaves your device since it's all on-device inference.

The interesting technical challenge was the clustering logic. I ended up using a union-find (disjoint set) structure combined with NaturalLanguage embeddings to figure out which notes are actually related, then merge them into clusters that update as you add more notes. Getting the similarity threshold right so Clouds don't over-merge unrelated notes or fragment obviously-related ones took a lot of tuning.
Demo video (56 sec, shows the auto grouping)
Curious if anyone else here has worked with Apple's on-device Foundation Models yet how are you handling similarity/clustering tasks, and did you run into similar tuning headaches with thresholds?

This is an OS (operating system) for brands. It helps companies avoid data loss, take a structured approach to marketing and brand building, and find the right communication channels.

Branditex v 0.2

A lot of AI products stop at generate.

But real work also involves coordination.

That s why calendar workflows are part of Provoke.

Inside the product, calendar isn t treated like an isolated plugin.