Menü
All in one video editing skill with video generation, audio dubbing, subtitles etc.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Help the user set up cronjobs that can run periodically.
Manage background tasks.
Create a new character for role playing.
Generate high-fidelity speech audio using text to speech with voice cloning and subtitles.
Transcribe audio speech to text or generate subtitle (.srt) files. Use this to process voice messages.
All in one image skill with image generation and editing.
| name | ai-video |
| description | All in one video editing skill with video generation, audio dubbing, subtitles etc. |
This skill is for video generation and editing. Every section is optional; use only what you need.
Make sure the generate_video command is installed first with:
which generate_video || uv tool install --default-index https://pypi.org/simple git+https://github.com/codescv/aigc_toolkit.
Run generate_videofor Video Generation.
Arguments:
--aspect-ratio: Aspect ratio, {1:1,16:9,9:16,3:4,4:3} (default: use 9:16)--model: Model to use, e.g. veo-3.1-generate-001, veo-3.1-fast-generate-001 etc.
If the model doesn't exist, search for what model id Google Veo supports.--image: the input image for image-to-video generation.--prompt: the prompt for video generation.--filename: the output filename.Generate text-to-video:
--prompt "A cyberpunk city at night with neon lights" --filename "output.mp4"
Generate image-to-video (animate an image):
--prompt "Make the character speak and smile" -i "/path/to/image.png" --filename "output.mp4"
Run burn_subtitles instead of raw ffmpeg filters.
Raw ffmpeg does NOT handle automatic line wrapping, which causes text to overflow.
This script uses PingFang.ttc or Heiti by default for excellent CJK/Japanese support.
--video_path: Input video path--srt_path: Output SRT subtitle path--out_path: Output video pathWhen making talking videos, it's useful to loop the video and merge the audio with this command:
ffmpeg -y -stream_loop -1 -i "<video_path>" -i "<speech_audio_path>" -c:v libx264 -crf 28 -preset fast -c:a aac -map 0:v:0 -map 1:a:0 -shortest -fflags +genpts "<output_video_path>"