Menu
Generate lip-synced avatar video from text using OmniHuman v1.5. Use when creating talking-head or avatar videos.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Send and read emails via Gmail browser automation. Use when asked to send email or check inbox.
Schedule tasks using natural language time expressions. Use when asked to schedule a recurring or timed task.
Generate voice-over audio using OpenAI TTS. Use when creating narration or voice for videos.
Render videos using Remotion compositions. Use when creating or generating videos.
Research topics for video content creation. Use when researching ideas for videos.
Write video scripts with hooks, structure, and timing. Use when creating scripts for videos.
| name | avatar-video |
| description | Generate lip-synced avatar video from text using OmniHuman v1.5. Use when creating talking-head or avatar videos. |
| allowed-tools | ["Bash","Read","Write"] |
Generate lip-synced avatar videos from text using the OmniHuman v1.5 pipeline.
Text → TTS → Audio → CDN Upload → OmniHuman → Video → Post-Processing → Final Video
python video-pipeline/voice_generator.py "Your script text here" output/voice.mp3
Options:
--voice nova (default: nova)python video-pipeline/storage_manager.py output/voice.mp3 assets/avatar.png
Returns:
python video-pipeline/video_generator.py <audio_url> <image_url>
Returns:
OmniHuman v1.5 settings:
python video-pipeline/video_retriever.py <video_url> output/avatar.mp4
Add background music:
python video-pipeline/post_processor.py output/avatar.mp4 assets/music/bg.mp3 output/final.mp4
Options:
--music-volume 0.15 (15% volume, default)--trim-start 0 (trim seconds from start)--trim-end 0 (trim seconds from end)# Step 1: Generate voice
python video-pipeline/voice_generator.py "Hello! Welcome to my channel. Today I'm going to show you something amazing." output/voice.mp3 --voice nova
# Step 2: Upload to CDN (capture URLs)
URLS=$(python video-pipeline/storage_manager.py output/voice.mp3 assets/avatar.png)
AUDIO_URL=$(echo "$URLS" | grep audio | cut -d' ' -f2)
IMAGE_URL=$(echo "$URLS" | grep image | cut -d' ' -f2)
# Step 3: Generate video
VIDEO_URL=$(python video-pipeline/video_generator.py "$AUDIO_URL" "$IMAGE_URL")
# Step 4: Download
python video-pipeline/video_retriever.py "$VIDEO_URL" output/avatar.mp4
# Step 5: Add music
python video-pipeline/post_processor.py output/avatar.mp4 assets/music/background.mp3 output/final.mp4
For best results:
| Setting | Value |
|---|---|
| Resolution | 720p (1280x720) |
| FPS | 25 |
| Codec | H.264 |
| Audio | AAC 128kbps |
| Component | Cost |
|---|---|
| OpenAI TTS (1000 chars) | ~$0.015 |
| fal.ai OmniHuman (per video) | ~$0.10-0.50 |