Upload one photo, AI writes your script, clones your voice, and generates a professional talking-head video. Powered by HeyGen + Jimeng OmniHuman. 12 languages. Free tier: 3 videos/day. Pro: $3.99/mo unlimited.
Wispr Flow: Dictation That Works EverywhereStop typing. Start speaking. 4x faster.
Promoted
Maker
📌
Hey Product Hunt! 👋
I'm a solo founder from Guiyang, China. Three months ago I got tired of paying for 5 different tools just to make one talking-head video. So I built JingShen.
What it does: Upload a photo → AI writes your script → clones your voice → generates a lifelike talking-head video → one click to publish on TikTok/YouTube/Bilibili. All in one workflow. No camera. No crew. No editing.
Why it's different:
All-in-one pipeline (not 5 separate tools stitched together)
12 languages — your AI avatar speaks them all
$3.99/mo unlimited (HeyGen charges $24)
BYOK model — use your own API keys, we take zero commission
PayPal global checkout
Tech stack: FastAPI + Vanilla JS + SQLite on a $6/mo HK server. Zero frameworks. Zero VC.
For the PH community: I'm giving away 3 months of Pro free — just DM me on X or reply here with your account email and I'll upgrade you. No catch, just want real feedback.
Happy to answer any questions! 🙏
Report
No reviews yetBe the first to leave a review for JingShen (境身)