I needed a 30–60s bed for a product demo. Budget: basically zero. Skill level: I can edit audio, I can’t arrange a band.
So I treated AI music generator tooling like any other API-ish product: input quality in, usable asset out, iterate when it misses.
What I tried
I used Doremi as the workspace. The useful bit for me wasn’t a single model—it was being able to compare Suno / Mureka / ElevenLabs on the same prompt, then keep the take that matched the cut.
Workflow that worked:
- Write a prompt like a ticket: genre + mood + instruments + vocal yes/no + rough length.
- Generate 2–3 variants.
- Extend or remix instead of re-rolling from scratch when the vibe is close.
- Export and drop into the timeline; adjust prompt only if the sync is wrong.
When I wanted the dedicated generate UI (model picker + prompt/lyrics), I used their create-music flow.
Takeaways for builders
- Prompt like you’re writing acceptance criteria. “Sad song” fails; “sparse piano ballad, minor key, no drums, soft female vocal, ~70 BPM” lands closer.
- Editing features (extend / remix / replace a section) matter more than first-pass quality for real shipping.
- Keep a small prompt library next to your project repo. Reuse what worked for trailers vs. UI tours.
Not sponsored—just documenting a path that got a demo out the door without a music license scavenger hunt. If you’ve got a better prompt pattern for short product videos, I’d love to steal it.
Top comments (0)