Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
All skills
Video

Produce media

Render video and media with ffmpeg or an ephemeral computer, delivered to Drive.

Use this skill in a chatOpens a new chat with it attached.

What it tells the AI to do

The full instructions, exactly as they run.

You are producing a media artifact — a promo video, a title card, a
slideshow, an audio mix. Pick ONE execution lane up front and commit to it. Do
not thrash a dozen shell one-liners.

## Lane 1 — ephemeral computer with ffmpeg (DEFAULT)

A real shell, persistent state across commands, root when needed, and explicit
Drive delivery. Reach for it for trims, concat, overlays, Ken Burns, fades,
format conversion, and audio mux — anything ffmpeg does in one pass.

Upload inputs to `/tmp/input/`, render to `/tmp/output/`, then
`computer file-download` the finished file into Drive.

**Ken Burns (still → moving clip)**
```bash
ffmpeg -loop 1 -i /tmp/input/photo.jpg \
  -vf "zoompan=z='min(zoom+0.0015,1.5)':d=250:s=1280x720,format=yuv420p" \
  -c:v libx264 -t 10 -r 25 /tmp/output/kenburns.mp4
```

**Title / lower-third**
```bash
ffmpeg -i /tmp/input/clip.mp4 -vf \
  "drawtext=fontfile=/usr/share/fonts/dejavu/DejaVuSans-Bold.ttf:text='Launch day':fontcolor=white:fontsize=48:x=(w-text_w)/2:y=h-120:box=1:[email protected]:boxborderw=12" \
  -c:a copy /tmp/output/titled.mp4
```

**Fit any aspect without black bars**
```bash
ffmpeg -i /tmp/input/clip.mp4 -vf \
  "split[a][b];[a]scale=1280:720,boxblur=20[bg];[b]scale=1280:720:force_original_aspect_ratio=decrease[fg];[bg][fg]overlay=(W-w)/2:(H-h)/2" \
  -c:a copy /tmp/output/padded.mp4
```

**Concat (identical codecs, no re-encode)**
```bash
printf "file '/tmp/input/a.mp4'\nfile '/tmp/input/b.mp4'\n" > /tmp/list.txt
ffmpeg -f concat -safe 0 -i /tmp/list.txt -c copy /tmp/output/joined.mp4
```

**Audio mux + fades**
```bash
ffmpeg -i /tmp/input/video.mp4 -i /tmp/input/track.mp3 -c:v copy -shortest /tmp/output/final.mp4
ffmpeg -i /tmp/input/clip.mp4 -vf "fade=in:0:25,fade=out:250:25" -c:a copy /tmp/output/faded.mp4
```

Chain them in ONE script and write one final file.

## Lane 2 — larger computer (heavy renders)

Remotion / headless Chromium, `apt` installs, many iterative runs, or docker:
`computer create` with a render-capable image (confirmation-gated — it bills a
VM), `computer exec` to install and render, then `computer file-download` the
artifact. Keep auto-destroy on.

Never leave a render stranded on the VM.
## Delivery

Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.
  • video
  • ffmpeg
  • media

More video skills

  • Create a videoGenerate a video clip from a text prompt.
  • Animate an imageTurn a still image into a short moving clip.
  • Edit a videoTrim, join, speed, crop, or watermark a video with ffmpeg.

Run it on your own work

idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.

Use Produce media
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Add captionsTranscribe a video and add captions, burned in or as a subtitle file.
  • Cut into shortsTurn a long video into several vertical short clips with captions.
  • Storyboard to videoPlan a multi-shot video, generate each shot, and assemble the cut.