Models / Seedance / Lip sync

Seedance lip sync prompting guide

How to prompt Seedance in lip sync / dialogue mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

speaker binding→action before line→dialogue quoted→voice tone→ambient audio

• Formula: precise subject + action details + scene/environment + lighting & colour tone + camera movement + visual style + image quality + constraints. source ↗
• Open with a one-paragraph summary (duration, aspect, one continuous shot, what the first frame looks like and where the last frame lands), then lock subject/world with numbers (8 metres, 85-200mm, golden-hour side sun), then timestamped blocks. community source ↗
• Time-segmented prompts for 10 s+: '0–3s: … 3–6s: … 6–10s: … 10–15s: …'. community source ↗

What the text should describe

• generate_audio true yields lip-synced speech (fal Seedance 2.0). source ↗
• Storyboard shots include audio per shot; keep dialogue in one language. source ↗
• Community tip: for better lip sync, render the voice externally and pass it as a reference VIDEO (black screen + audio) instead of an MP3 audio ref; the video is time-coded. community source ↗
• Dialogue lines tagged with the speaker and a parenthetical action/tone: 'Cat host (licking paw, rolling eyes): "…"'. community source ↗

What not to describe

• Don't mix Chinese and English in dialogue except proper nouns. source ↗

Camera vocabulary

• Standard terms work (medium shot, close-up, slow push-in, smooth lateral tracking, fixed shot). Use ONE camera movement per shot; combining push, pull, pan and move raises instability. source ↗

Responds well to

• Name body parts with range, speed and force (slowly raise a hand, quickly turn the head); prefer slow, continuous movement; show emotion through physical detail, not 'very sad'. source ↗

Duration and limits

• fal Seedance 2.0: duration 4–15 s or 'auto'; 480p/720p/1080p/4k; aspect auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; generate_audio default true. source ↗

Multi-shot

• Complex clips: timeline storyboard 'Shot 1 / Shot 2 / Shot 3', each with who + where + doing what + camera + audio; don't force per-shot durations. source ↗

Avoid and failure modes

• Constraint phrases: 'keep it subtitle-free', 'avoid generating any text or subtitles', 'do not generate a logo', 'do not generate a watermark'. Subtitles cannot be suppressed 100%. source ↗
• Keep dialogue in one language; avoid mixing Chinese and English except proper nouns. source ↗
• Prefer positive mechanisms over long negative lists ('enters through the rear doorway' not 'do not teleport'); keep a few targeted exclusions for observed failures and place each rule next to the event it governs. community source ↗
• Don't ask for 'static camera' and 'orbit' in the same segment; don't overload 4–5 s with many scenes. community source ↗

Negative prompt

Not supported; describe what you want instead. source ↗

Real prompts, credited

Seedance 2.5 Prompt:
Animate @[char1 ref]  as Neri, 24, and @[char2 ref]  as her father Daro, 58. Preserve each reference's face, hair, outfit and proportions.

Visual style: animated painted forms with crisp contours and faceted light. Keep the references' long silhouettes, angular faces and broad clothing shapes, with restrained brush texture and expressive anime-influenced acting. Extend this treatment to the folded dragon skin and monumental stone tiers. Amber light cuts through teal dusk. The girl keeps youthful proportions.

30 seconds in a sixty-meter circular open-air arena with steep stone tiers and packed, continuous rows of spectators. A girl in a moss-green cap stands between seated adults in the east front row, immediately behind the arena's continuous guardrail. Her left hand grips the rail; her right holds one ivory paper flower with folded petals and a rolled stem. The tw

Cat host (licking paw, rolling eyes): "Who understands my suffering?…" Dog host (head tilted, tail wagging): "You're one to talk?…"

Next

Sources

• docs.byteplus.com/en/docs/modelark/seedance-2-0-prompt-guide
• docs.dev.runwayml.com/api/
• fal.ai/models/bytedance/seedance-2.0/image-to-video/api
• fal.ai/models/bytedance/seedance-2.0/reference-to-video/api
• github.com/dexhunter/seedance2-skill/blob/main/SKILL.md
• github.com/mattvideoproductions/MVP-Prompts/blob/main/seedance25_prompting_guide.txt
• x.com/DTCtalent_/status/2108907785354154465