Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from bundle
Generate talking-head avatar videos from text. Pipeline: ElevenLabs V3 TTS → OmniHuman 1.5 lipsync → Kling v3 motion enhancement.
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
agents/openai.yaml
1interface:2display_name: "Avatar Video from Text"3short_description: "Generate a talking avatar video from text + character photo + voice"4default_prompt: "Use $avatar-video-from-text to generate a talking-head video. Provide text, a character image, and an ElevenLabs voice name or ID. The pipeline runs TTS → OmniHuman lipsync → optional Kling motion enhancement."5