Are micro-dramas AI generated? Six shots and a voice, $7.85
Yes, many are. A 60-second vertical micro-drama episode on Sume: six 10-second Wan 3.0 shots, TTS dialogue, Timeline and captions for $7.85.
Short answer
Some micro-dramas are fully AI generated, some mix actors with AI inserts, and the format is rising on TikTok, Reels and Shorts, as reported by HeyOrca. On Sume a 60-second episode is six 10-second shots, one voice track and one render.
| Step | What runs | Cost |
|---|---|---|
| 6 shots, 10 s each, 9:16, 720p | Wan 3.0 at $0.125 per second | $7.50 |
| Dialogue, about 900 characters | TTS at $0.0475 per 1,000 characters | $0.05 |
| Assemble shots and voice | Timeline, one output minute | $0.10 |
| Burn in captions | Video captions, up to 60 s | $0.20 |
| Episode total | $7.85 |
How the six shots are planned
Write each shot as one action and one camera move, and end shot 6 on the cliffhanger line. Wan 3.0 takes 2 to 30 seconds per job, so each 10-second shot is one job at $1.25.
Dialogue is the weak spot of video models: they do not lip-sync to generated TTS. If a close-up needs a speaking face, make that single shot with a still plus audio (see the lip-sync post below) and keep the other five as Wan shots.
- Keep the same character description in every shot prompt.
- Generate at 480p first at $0.0625 per second ($3.75 for all six) and re-run only the keepers at 720p.
Where it stops
Character consistency across shots is a prompt and reference-image discipline, not a switch. Budget two redo shots (about $2.50) per episode.
Sources
Related posts
More in Use cases
- ASMR-style AI video prompt: Gemini Omni with sound, 10 seconds
Prompt Gemini Omni for ASMR-style clips with close hand movement and quiet foley. Sume request, why audio cannot be switched off, and what 10 seconds costs.
- Avatar clips of 60 seconds or less and the Shorts one-minute line
YouTube allows 3-minute Shorts, but claims behave differently above one minute. Why a Sume avatar clip capped at 60 seconds sits on the safe side, with sources.
- Five-lesson avatar onboarding series: one handle, safe retries
Plan an onboarding series of short Sume avatar videos: one handle, one script and idempotency key per lesson, a preview first, and captions on the final MP4.
- B-roll for a podcast clip: five 5-second inserts for $3.46
Cut a 45-second podcast clip with AI B-roll: transcribe for $0.01, five Wan 3.0 720p inserts, Timeline and captions for $3.46 on Sume.
Written by Sume