Home › Prompts › Grok Imagine › Lip-synced dialogue scene with voice references

Lip-synced dialogue scene with voice references

A short talking scene with lip-synced speech, using reference images for characters and up to 3 voice references.

Grok ImagineVideoRuleStack original

Written for Grok Imagine Video 1.5 (grok-imagine-video-1.5) · Updated 2026-10-16

Note: Review and test before use. Provided as is, without warranty. See Terms.

[Duration, e.g. 10]-second scene. Reference image 1 is [character A]; reference image 2 is [character B]; voice reference 1 is A's voice, voice reference 2 is B's voice. Setting: [location]. Medium two-shot, slow push-in. A says: [line 1]. B pauses, then replies: [line 2]. Ambient sound: [ambience]. No music. Natural lip sync, steady handheld camera.

Replace everything in [square brackets] with your own details.

Settings & parameters

• API: grok-imagine-video-1.5, duration 1–15 s, resolution 1080p native, aspect 16:9 or 9:16
• Up to 14 reference images and 3 voice references; pin first, last and up to 4 mid frames
• Use grok-imagine-video-1.5-lite for cheap drafts without references

Variations

• Product explainer with one presenter and a pinned last frame showing the product.
• Vertical 9:16 version for Shorts.
• Extend the clip with grok-imagine-video video extension (adds 2–10 s).

Tips

• Use voices you own or have permission for; never clone a real person's voice without consent.
• Keep each line short so lip sync stays tight.