Pilot C2 — The Spoken Word

Pilot C2 — The Spoken Word is an 11-second, 16:9 3D CGI anime-forward game cutscene produced on the NepTrunia world board in Neta Studio. It is the quietest beat of the sequence: at the smoky stage of The Veil of Truth, Lyrica — the singer with the hooded black lace gown and the magenta-teal-violet hair — leans into the centre microphone and begins the song’s spoken-word intro, calm and close, as the room holds its breath. Raze stands still at the right mic, cigarette smoke curling from his hand, and the shadowy band waits motionless behind them.

The whole shot is a single slow cinematic push-in, from a medium of the stage to a medium-close on Lyrica, in the Final Fantasy VII Advent Children register: glossy semi-realistic 3D, warm stage light and rising embers, no photoreal, no 2D painting. One prompt and three locked reference images produced the entire shot with Seedance 2.0.

Watch it now: Pilot C2 — The Spoken Word →

11 seconds · 16:9 · 3D CGI anime-forward — rendered with Seedance 2.0 from the world’s own locked references in a single image-to-video pass. The brief asks for exactly one action — Lyrica leaning to the mic as the spoken intro begins — with no readable text, no signage, no visible faces among the band, and no duplicate character or extra limbs.

Download the MP4 →

“11 seconds. 3D CGI anime-forward game-cutscene style, Final Fantasy VII Advent Children register, not photorealistic, not 2D painting. Environment: the stage of The Veil of Truth, smoky bar stage, warm stage light, floating embers. Reference images: 'lyrica' is the female singer at the mic; 'raze' is the male singer at the other mic; 'stage_key' shows the full stage with shadowy band. Event goal: Lyrica begins the song's spoken-word intro into her microphone, calm and close, as the room holds its breath. Spatial blocking: Lyrica at the center microphone, one hand resting on the stand, leaning slightly in; Raze stands at the right microphone, still, cigarette smoke curling from his hand; the shadowy band waits motionless behind them. Camera: slow cinematic push-in on Lyrica from a medium shot to a medium-close, Raze and the band softly blurred behind her. One main action: Lyrica leaning to the mic as the spoken intro begins. Hard constraints: no readable text, no signs, no visible faces among the band, style stays 3D CGI anime-forward, no duplicate character, no extra limbs.”

Model: Seedance 2.0 — 11s, 16:9, 3D CGI anime-forward, generated from the world’s own Lyrica, Raze and stage references, with no readable text anywhere.

Neta Studio turns one line of direction into a finished cutscene. Lock the cast and the room with image models like GPT Image 2, clean the references up as transparent cut-outs, then hand the exact images to a video model like Seedance 2.0, Kling, Veo or MiniMax H3 — and every take comes back with the same faces, the same wardrobe and the same warm grade.

Iterate freely and keep only the best take. The approach pass, the spoken-word take and the continuation beat on this page are one scene shot three ways from the same locked references — switch models, reject a render, re-queue the same prompt, and publish a link that plays anywhere with no download.