This product was not featured by Product Hunt yet.
It will not yet shown by default on their landing page.
Krystal BradicichUpload any audio — a song, podcast, sermon, speech — and AudioSoul transcribes it word-for-word, timestamps every sentence, and generates a unique AI image for each one. Then exports it as a downloadable MP4 video, PDF storyboard, Built by a solo dev, $1 per generation, no subscription required.
Top comment
Hey PH! 👋 I'm Krystal, solo dev and founder of AudioSoul. I built this entirely as a single-page client-side app — 2,500 lines of code! — using Supabase edge functions, Grok, Pollinations, and Google OAuth. The idea came from wanting to make audio content visual without expensive video editors. Would love your honest feedback — what audio would YOU run through it first? 🎧
Comment highlights
I think that sounds like a great product, what are the costs for that type of thing?
The video creator I wish had existed sooner.
I've been making music with Suno.ai and loving every second of it — but turning those tracks into videos? That was eating up 30 hours I didn't have. So I built the solution myself.
This tool was built with pure HTML, CSS, and JavaScript. No frameworks. No libraries. No backend. No credit card. No login. Everything runs entirely in your browser — your music, your videos, your data. All yours, always.
Just great music, finally paired with great visuals. ✨