13. English audio-referenced line

When to use it: an English principal line. Here, a presenter for Fennick, an invented kitchen-appliance brand, delivers one dry line to the lens.

Methods:

• the English route (decided): see Speaking shots and lip sync → English lines and Seedance's own voice;

• Seedance's own voice. Option: use it when a principal line is in English or another language Seedance speaks well, and you choose it for the project [proven]: approved by the client from a sample made with one fixed voice description. Not chosen for this project, so the line is recorded and attached as an audio reference.

Shared rules: the rules every recipe keeps, and the five rules for speaking and singing shots (template and route, the camera during speech, the angle, the native reviewer, the placed voice): Video with Seedance → How to read a recipe.

References: 1 the presenter's sheet; 2 his identity close-up; 3 the kitchen counter's master plate; 4 the sealed manual's prop sheet; audio 1 the approved recording, voice only, 3.4 s of speech.

Settings: omni-reference · audio on · 5 s (start 0.5 s, speech 3.4 s long, ending at 3.9 s, tail 1.1 s) · 16:9.

Cost: 480p draft 15 cr (5 s × 3 cr) · 1080p finish 80 cr (5 s × 16 cr).

If Draft Mode refuses the audio reference: draft at 720p, for 35 cr.

After the finish: the returned audio is muted and the approved recording laid back. The lips are checked at full size, with one lip-sync pass only if they don't hold.

Budget: high risk (a readable face, a speaking line, one lip-sync pass inside the envelope): 310 cr expected (5 s × 62), 615 cr ceiling (5 s × 123).

What to change, what to keep: Template E (Speaking shots and lip sync → Templates C, E and F).

Yours to rewrite:

• the line, in quotation marks, exactly as recorded;

• the times, measured from your recording;

• the voice, in a few words.

Keep word for word: what recipe 12 keeps (Video with Seedance → 12. Arabic audio-referenced close-up).

SCENE CONTEXT: A bright kitchen. A presenter leans on the counter beside a sealed product manual and delivers one dry line to the camera.
ACTIVE REFERENCES: @image1 is THE PRESENTER: a man in his late thirties, lean, with short dark hair, a navy overshirt over a white tee; both hands resting flat on the counter. This sheet gives identity and wardrobe and nothing else: the face and hair come from the close-up panel alone, the wardrobe and body from the full-body panels alone; the front panel's cropped head is never repeated; leave out its grey ground, layout and flat light. Match it exactly. @image2 is THE PRESENTER'S FACE: the identity close-up, used for the face alone. @image3 is THE COUNTER: the pale wooden counter, the tiled wall and the window, as architecture, materials and light only; it does not decide where the camera stands. @image4 is THE MANUAL: a thick sealed manual with a plain white cover; design only; it is not a start frame. @audio1 is THE PRESENTER'S VOICE: the approved recorded line; it gives the voice, pace and pauses only, and nothing in the picture.
VOICE AND TIMING: THE PRESENTER, voice: dry, warm, mid-range, as @audio1. In @audio1 the speech runs 3.4 s; his line starts at 0.5 s and ends at 3.9 s.
FIRST FRAME AND BLOCKING (in motion from frame one): Medium close-up at the counter. THE PRESENTER is already settling his weight onto his forearms, lips closed, his eyes on THE MANUAL, which lies on frame left; both hands rest still on the counter.
FORMAT MODE: A single unbroken shot with no cuts of its own. Real time.
OPTICS: Medium close-up on a 47° diagonal field of view; his mouth clear and evenly lit; the kitchen soft behind him; the lens holds steady.
CAMERA: A slider at his eye height, 1.2 m from him. One very slow push of 20 cm across the 5 s, travelling, seen as his face growing by about a fifth, arriving just tighter as the dry smile comes; his face stays square to the lens.
ACTION / TIMELINE: 0–0.5 s his lips are closed and he glances at THE MANUAL; 0.5–3.9 s he speaks: his eyes come back to the lens on the second sentence, and a small dry smile arrives on the last word; 3.9–5.0 s his lips are closed and he holds the look and the smile, with one slow nod.
PERFORMANCE — THE PRESENTER: He wants the viewer to laugh along with him; his tactic is to say it flat and let the last word land. His gaze stays engaged, his pupils move, his blinks are uneven. A dry, warm deadpan, never a grin. THE PRESENTER says, deadpan: "Nobody reads the manual. So we made it… pointless."
Only THE PRESENTER speaks. Only words between quotation marks are said aloud; everything else is direction.
TEXTURE: Knife marks and one oil stain in the pale wooden counter; worn grout in the tiled wall.
LIGHTING: A single soft window key, from camera left, 5600 K, 2:1; a pale bounce off the wall under his chin; exposed for his face, the mouth evenly lit.
AUDIO: His voice, pace and pauses follow @audio1; close, dry dialogue; the quiet hum of the kitchen and the slow tick of a clock, low. No music, no subtitles and no on-screen text.
STYLE: A bright, modern commercial look: clean blacks, warm neutral colour, soft contrast, true skin texture; light seen only where it lands, as highlights and reflections on real surfaces.
POSITIVE LOCKS: Exactly one speaker and one manual. His hands stay still on the counter. The manual's cover stays plain white, with no readable text. No subtitles.

Check the take

Lay the approved recording back on the timeline and play the window at full size: the lips must hold on every word. Check the words against the approved line.

Common failure and fix: the lips drift off the laid-back recording, because Seedance re-timed the line. Give the shot its one lip-sync pass to the recording.

Sources

• @adilinthewildtempo (blog): the mapping of each reference to one panel's job in the character role lines.

• Tigran Mutafyan and the Higgsfield studio's acting work: acting as a task.