operator-first · human in the loop

Stories that find
their light.

Lumyra turns a topic, an idea, raw text, or reference photos into a narrated short-form video, reviewed step by step and never paid for blind.

meaning first · model and budget after
Lumyra animated brand loop
8 modes research · fiction · news · 5 more
9 video models Seedance · Kling · Sora · 6 more
7 review gates paid steps are human-approved
9:16 locked aspect TikTok · Reels · Shorts ready
The pipeline

Seven steps. Every paid one,
reviewed.

Lumyra is built operator-first. There is no autopilot mode that quietly burns money on a bad script. The system stops before each spending step and waits.

01step

Choose a mode

research · fiction · news · idea · text · photos

02step

Generate or import a script

LLM drafts · operator approves or revises

03step

Build a visual plan

scene-by-scene with global direction

04step

Review before paying for assets

everything paid is visible first

05step

Generate stills then animated clips

Seedance · Kling · Sora · 6 more

06step

Approve hero and failed scenes

rust-tinted warnings, never silent

07step

Assemble · QA preview · publish

Telegram · TikTok · Reels · Shorts

Models · routed at choose-time

Pick the model that fits
the story.

Each video model exposes its per-second price before generation. Duration, generated audio, and final length are visible before spend.

Seedance 2

fal.ai · ByteDance
recommended$0.038/s

Kling 2.5

fal.ai · Kuaishou
premium$0.052/s

Kling 1.6

fal.ai · Kuaishou
stable$0.036/s

Wan 720p

fal.ai · Alibaba
value$0.024/s

Hailuo

fal.ai · MiniMax
expressive$0.032/s

Sora

OpenAI
lab$0.060/s
Pricing · transparent

Everything paid
is visible first.

Before model spend, Lumyra shows line items: script, plan, references, video, voiceover, generated audio, assembly. The Lumyra outro is included.

Estimate

6 clips · 10s

Seedance 2 · 9:16 · 60s output

$3.15 before tax
Script LLM$0.08
Visual plan$0.11
Reference images$0.27
Video · 6 × 10s$2.28
Voiceover$0.27
Assembly$0.05
Lumyra outroincluded
Why Lumyra

“Voice stays dominant. Generated audio is mixed quietly under narration, around -18 dB by default.”

excerpt from the operator console

Open Lumyra in Telegram.

The bot does the heavy lifting. The web app keeps the studio.

@lumyra_factory_bot