You can turn a handful of photos and a music track into a finished, post-ready video for free — no watermark, no subscription, no auto-upload. This guide shows how to do it with ViralMint, a free, open-source desktop app for macOS, Windows, and Linux. You supply the pictures (your own or AI-generated), pick music (a bundled royalty-free track or an AI-generated song), and export a clean mp4 you download and post yourself.

The fastest way to make a video with photos and music

The core idea is simple: each photo becomes a scene, ViralMint adds subtle motion to each still, mixes music underneath, and stitches everything into one clip. This runs through Smart Video, the short-form creation pipeline in the app. It’s not a heavy timeline editor with drag-and-drop transitions — it’s an automatic pipeline that gets you from “folder of photos” to “finished mp4” in a few minutes.

Here’s the honest scope: motion is applied automatically (a Ken Burns zoom-and-pan), and clips are joined with FFmpeg. There’s no manual per-transition editing — you trade fine control for speed and a consistent, polished look.

Step 1: Gather or generate your photos

Start with the images you want. Vacation photos, product shots, screenshots, quotes — anything. Five to fifteen works well for a short: enough variety without any single shot dragging.

Don’t have the right pictures? Generate them from a text prompt with Nano Banana at $0.06 per image. That’s useful when you need a specific look — a themed background, an illustration, a concept shot — that you can’t photograph. You can mix generated images with your own in the same video.

Step 2: Add the photos to Smart Video

Upload your images into Smart Video. Each still is treated as a scene the app will animate and stitch. If you generated AI images, they slot in alongside your uploads.

Step 3: Pick your music

This is the “and music” half. You have two options:

  • Bundled royalty-free library (free) — choose from lo-fi, cinematic, upbeat, ambient, or corporate. These are cleared for TikTok, YouTube, and Reels, so no copyright claims.
  • AI-generated song ($0.15) — generate an original track with Lyria 3 Pro when you want something custom.

Either way, the music is mixed under the visuals and faded in and out automatically, so you don’t have to touch audio levels.

Step 4 (optional): Add voiceover and captions

If your video needs narration — a story, an explainer, a caption read-aloud — add a voiceover. Free options include Edge TTS; paid options include Gemini 3.1 Flash TTS or an on-device cloned voice. When there’s narration, local Whisper times word-by-word captions to the audio, so your captions land exactly on the spoken word. Captions are optional — skip them for a pure photo-and-music montage.

Step 5: Ken Burns motion applies automatically

A static photo held on screen looks flat. ViralMint applies a subtle Ken Burns effect — a slow zoom and pan — to each image so the frame feels alive. This happens automatically; there’s no keyframing to do.

Step 6: Choose your aspect ratio

Pick the shape for where you’re posting:

  • 9:16 — TikTok, Instagram Reels, YouTube Shorts
  • 16:9 — YouTube, landscape players
  • 1:1 — square feed posts

Step 7: Export the mp4 and post it

Export the finished video. ViralMint hands you a downloadable mp4 with no watermark. There’s no auto-upload — you post it yourself, which keeps you in control of captions, timing, and which account it goes to.

What it costs

For most people, this is free. Photos you already own plus a bundled royalty-free track (plus free Edge TTS if you want narration) cost nothing beyond the app itself. Costs only appear when you add AI extras:

  • AI-generated images: $0.05 each (Nano Banana)
  • AI-generated song: $0.15 (Lyria 3 Pro)

AI features require a free account and a small pay-as-you-go prepaid balance. New accounts also get a modest free daily allowance to try things before topping up. There’s no subscription — you pay per action only when you use paid AI.

When ViralMint is the right tool (and when it isn’t)

Reach for this when you want a fast, clean photo video maker that outputs vertical or square shorts with music and optional captions — the kind of clip you post to social. The automatic Ken Burns motion and FFmpeg stitching give a consistent look without editing skills.

If you need frame-by-frame timeline editing, custom per-slide transitions, or precise photo-transition choreography, this isn’t a dedicated slideshow editor and won’t replace one. ViralMint optimizes for speed and a good default, not manual fine-tuning.

Ready to turn your photos into a video? Download ViralMint free for macOS, Windows, or Linux.