manim-composer
adithya-s-k
Turn math video ideas into scene-by-scene plans.
Educational video planning
Video & audio skills for AI agents
Producing, editing and understanding video, music and speech. Video production Skills build videos scene by scene from code with HyperFrames and Remotion; generation Skills drive AI clip models; audio Skills compose music, synthesise voices and transcribe recordings into timed captions.
Sort by
Most installed
578 Skills
Showing Skills in Video & audio.- 2.2k
2.1kchat-with-anyone
noizai
Hear roleplay replies in a matching synthetic voice.
Voice roleplay
2kprompt-videos
replicate
More precise video prompts, from scene to sound.
Video prompting
2knemotron-speech
nvidia
Deploy, test, and tune Nemotron Speech workflows.
Speech engineering
- 2k
video-translation
noizai
Hear translated dialogue while the original video stays intact.
Video translation
2kjianying-editor
luoluoluo22
Turn your editing ideas into JianYing video drafts.
Video editing
JI
2kscribe
anthropics
Turn recordings into usable transcripts.
Media transcription
- 2k
physical-ai-video-data-augmentation
nvidia
Turn your videos into labeled training variants.
Video data augmentation
+1 - 2k
build-zoom-video-sdk-app
anthropics
Build custom video sessions with full UI control.
Video app development
- 2k
build-zoom-meeting-app
anthropics
Build your meeting flow with the right SDK.
Video conferencing
- 2k
vss-summarize-video
nvidia
Your recorded video, summarized with timestamped events.
Video analysis
VS 
1.9kcomfyui-workflow-builder
mckruz
Turn your image and video ideas into workflow JSON.
Generative media
- 1.9k
vss-ask-video
nvidia
Get answers that require a fresh look at your video.
Video analysis
VS+1 
1.9kdouyin-video
yzfly
Save Douyin videos and turn their speech into text.
Video transcription
+1
1.9kbibi
jimmylv
Turn long videos into notes you can skim.
Video summarization
- 1.9k
vss-search-archive
nvidia
Find the moments you need in your video archives.
Video search
+1 - 1.9k
vss-generate-video-report
nvidia
Turn video clips or incident ranges into structured reports.
Video analysis
VS - 1.9k
daily-news-caster
noizai
Your headlines, turned into a two-host podcast.
News podcasting
NA 
1.9kaudio-setup-mixers
unity-technologies
Your audio sources, sorted into sensible mixer groups.
Audio routing
- 1.9k
vss-deploy-detection-tracking-2d
nvidia
Deploy video tracking and manage its streams.
Video perception
+2 - 1.9k
vss-deploy-video-embedding
nvidia
Deploy RT-Embed and turn video into searchable embeddings.
Video search
+1 - 1.9k
vss-deploy-dense-captioning
nvidia
Deploy RT-VLM and turn video into dense captions.
Video captioning
+1 - 1.9k
vss-manage-video-io-storage
nvidia
Manage cameras and retrieve recorded clips with VIOS.
Video operations
+2 
1.8kdouyin-video-summary
liu-wei-ai
Turn Douyin videos into structured text summaries.
Video summarization
+1
Yes. Video production Skills build scenes from a script and assets, and video generation Skills can create the footage itself from descriptions.
Several, including Wan, Seedance and others; each generation Skill names the model it drives and what that model is good at.
Yes. Transcription Skills turn speech into text, with timestamps for captions, and some summarise the result.