Models / Runway / Lip sync

Runway lip sync prompting guide

How to prompt Runway 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

avatar→script or audio→voice

• T2V: '[Camera] shot of [subject] [action] in [environment]. [Supporting descriptions]'. Structure matters less than removing ambiguity. source ↗

What the text should describe

• Characters (gwm1_avatars): pick avatar {type: runway-preset, presetId} or a custom avatarId, then speech {type:'text', text, voice} (TTS) or {type:'audio', audio}. There is no scene prompt; the script IS the prompt — write it as spoken lines. source ↗

What not to describe

• Not a cinematic dialogue generator: no camera/scene prompt field. For scene dialogue on Runway's API use a hosted model with audio (Veo 3.1, Seedance 2.x). source ↗

Camera vocabulary

• For still shots: 'The locked-off camera remains perfectly still.' source ↗

Responds well to

• Sequential prompting: 'X, then Y. Finally, Z.' or '[00:01] X. [00:03] Y.' source ↗

Duration and limits

• Chain longer sequences: last frame of one generation as the next image input. source ↗

Avoid and failure modes

• Positive, concrete phrasing; no conflicting instructions; very long multi-paragraph prompts over-constrain. source ↗
• Unwanted cuts = duration too short; add 'Continuous, seamless shot'. source ↗

Negative prompt

Supported via .

Real prompts, credited

Turn this into a 4-shot AI video plan for Runway, 16:9.
     "A courier hesitates outside a Republican-era Shanghai apartment door
      before knocking, then slips an envelope under it and walks away."

Handheld, slightly shaky vlog-style footage
Want me to tailor it for a specific model (Sora, Veo, Runway, Kling)? They each respond a bit differently to camera/style phrasing.

"Camera focuses on a small circle of neon light in a pitch dark space, the light explodes into waves of beautiful neon energy that silhouettes mountains".

Next

Sources

• academy.runwayml.com/guides/prompting-guide
• docs.dev.runwayml.com/api/