Pilot C2 — The Spoken Word — AI Music-Film Cinematic
Watch Pilot C2 — The Spoken Word — an AI-generated 11-second music-film cinematic from Neta Studio. Gothic singer Lyrica begins her spoken-word intro at the smoky bar stage of The Veil of Truth while Raze waits at the second mic, as a slow camera push carries the shot from medium to medium-close. Rendered with Seedance 2.0 from the world's own 3D CGI reference frames. Plays free in your browser, no download.
Final Video: Pilot C2 — The Spoken Word
Pilot C2 — The Spoken Word is an 11-second, 16:9 AI music-film beat produced on the NepTrunia world board in Neta Studio. On the smoky bar stage of The Veil of Truth — a venue that exists inside a man's mind — Lyrica, the gothic singer with rainbow-streaked hair and glowing cyan eyes, leans into the center microphone and begins the song's spoken-word intro. Raze, the tattooed male singer, waits at the second mic with a cigarette; behind them the shadowy band holds motionless. One camera, one slow push-in from a medium shot to a medium-close, no cuts.
Watch it now: Pilot C2 — The Spoken Word →
The Video
1920×1080 (16:9) · 11s · 24 fps · one slow push-in — rendered with Seedance 2.0 from the world's own locked reference frames, in a 3D CGI anime-forward game-cutscene look (Final Fantasy VII Advent Children register): not photorealistic, not a 2D painting, no readable text, no visible faces among the band.
How It Was Made
Production Process Breakdown
Three reference renders locked every identity before anything moved: Lyrica at the center mic, Raze at the second mic, and stage_key — the wide of The Veil of Truth stage with two vocal mics and a shadowy backing band (guitar, bass, drums, violin). Re-rendered as 3D CGI characters in the AAA game-cutscene style, these three frames are the DNA every pilot beat shares.
The first takes established the space and the approach. Pilot C1 — The Room Finds the Stage (10s) glides from the back of the half-dark room, faceless patrons in silhouette, and ends as Lyrica steps up to her mic; H3 Meter — Lyrica Steps to the Mic (15s) was the earlier, longer meter of the same drift. Both proved the camera language and the character lock before the close-up work began.
This is the beat this page is built around. Pilot C2 — The Spoken Word (11s) starts where the approach ends: Lyrica is already at the center mic, one hand on the stand, leaning slightly in as the spoken-word intro begins. The camera pushes slowly from medium to medium-close while Raze stays still at his mic and the band waits in silhouette. Calm, close, one continuous move.
The beat after it proves the sequence reads as one continuous scene. Pilot C3 — The Band Kicks In (12s) opens the moment the spoken word ends: the drummer hits, the lights come up, and Lyrica begins to sing her first line while the shadowy band springs to life behind her. Cut together, C1 → C2 → C3 form a single unbroken musical moment from the same locked frames.
A parallel pilot, C4 — He Finally Found People (15s), left the stage entirely: the same man rendered ordinary — bald, goatee, black tee — sitting in a gray lunchroom among faceless coworkers, quietly almost-smiling. It exists to prove the identity lock survived across worlds: the tattooed stage singer and the quiet man are unmistakably the same person, and the film can cut between them without losing the audience.
Generation Prompt
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 — image-to-video from the Lyrica, Raze and stage_key reference frames, 11s single push-in @ 1920×1080 (16:9).
Asset Prompts
The same woman as the reference image — Lyrica, the female singer — re-rendered as a 3D CGI character in the Final Fantasy VII Advent Children / AAA game-cutscene style: anime-forward, NOT photorealistic, NOT a 2D painting. Preserve her design exactly: long black hair with vivid rainbow streaks (teal, purple, pink), glowing cyan eyes, black gothic lace-and-chain outfit, choker, forearm tattoos. Clean smooth stylized skin, soft subsurface glow, expressive anime-proportioned eyes. She stands at a microphone on the stage of a smoky bar, warm stage light and floating embers, dimensional 3D modeling, clean controlled materials, cinematic volumetric lighting, premium game-cinematic render. Waist-up, facing camera. No text, no watermark.
The same man as the reference image — Raze, the male singer — re-rendered as a 3D CGI character in the Final Fantasy VII Advent Children / AAA game-cutscene style: anime-forward, NOT photorealistic, NOT a 2D painting. Preserve his design exactly: bald head, goatee, full neck and arm tattoos, layered silver chain necklaces, black zip-up hooded jacket over a black tee, cigarette in hand, intense watchful eyes. Clean smooth stylized skin, dimensional 3D modeling, controlled materials, cinematic volumetric lighting. He stands at a microphone on the stage of a smoky bar, warm stage light and floating embers, premium game-cinematic render. Waist-up, facing camera. No text, no watermark.
Key-frame reference for an animated music video in the Final Fantasy VII Advent Children / AAA game-cutscene style — 3D CGI, anime-forward, NOT photorealistic, NOT a 2D painting. Scene: the small stage of The Veil of Truth, a smoky bar stage inside a man's mind. Two vocal microphones on stands at center front. Behind them the shadowy backing band — a guitarist, a bass player, a drummer at a drum kit, and a violinist — figures with NO facial definition, dark silhouettes half-lit by stage glow. Amps and cables, warm ember particles drifting in the air, neon light bleeding in from the bar beyond. Foreground darkness hints at bar tables and chairs. Cinematic volumetric lighting, dimensional 3D modeling, clean controlled materials, premium game-cinematic render. Wide establishing composition. No text, no watermark.
Reference Frames
Why Choose Neta Studio
Neta Studio turns one board into a music film. Build the world, lock the characters with image models like GPT Image 2, hand the exact reference frames to video models like Seedance 2.0, Kling and Veo — and every beat comes back with the same faces, the same stage, the same light.
Cut, reject and re-take as much as you need. The approach takes, the spoken-word beat and the follow-through above are one continuous scene shot in pieces — iterate beat by beat, then share a link that plays anywhere, no download.
Studio Interior
Start Creating
Pilot C2 — The Spoken Word was generated by Neta Studio AI from reference frames and one prompt — the world board, the character renders and the film all took minutes. You can do it too: step onto the same stage or start fresh from any idea. No coding required, free to start.