MIT-licensed agent skill that automates Vox-style paper-collage explainer videos from a single topic on Atlas Cloud + local ffmpeg; install it into any coding agent's skills folder — including DeepSeek Harness workflows.
DSH integration
Compatible
Inferred
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Turn a one-line topic into a finished Vox-style paper-collage explainer or ad video
A final MP4 with script, collage keyframes, motion, voice-over, music and captions, assembled at out/<project>/final.mp4 after two human approval gates
Creators and marketers using DeepSeek Harness or another coding agent who need editorial-style explainer/ad videos without hand-editing them
Re-style existing footage or photos into the collage look (A-roll / C-roll)
Talking-head videos re-styled frame-for-frame while keeping the real face, lip-sync and gestures; still photos cut out as photographic stickers anchored into generated posters, with optional voice-cloned narration
Video producers and brand teams that already have talking-head footage or product shots and want the Vox collage aesthetic
02How to install into DeepSeek Harness
Prerequisites
- A coding agent — Claude Code, Codex, or similar
- An Atlas Cloud API key
- ffmpeg + ffprobe (e.g. `brew install ffmpeg`)
- Python 3 with Pillow (`pip install pillow`) for caption/watermark overlays
Installation steps
- 01
Option A — clone the repo as a skill: `git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director`
$ git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director
- 02
Option B — download `vox-director.skill` and install it via your Claude skills UI
- 03
Set your Atlas Cloud API key: `export ATLASCLOUD_API_KEY="sk-..."`
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Agent skill (SKILL.md workflow + scripts) installed into a coding agent's skills directory; the README targets any coding agent and does not mention DeepSeek Harness explicitly, though the repo is tagged dsh-plugin.
End-to-end video pipeline with human gates
A one-line topic (B-roll), a talking-head video (A-roll), or a still photo (C-roll)→beat map → style bake-off → collage keyframes → motion → voice + music → ffmpeg assembly → final.mp4
Sends prompts and media to the Atlas Cloud API (network calls to api.atlascloud.ai)Writes generated assets and final.mp4 under out/<project>/Three input modalities (B-roll / A-roll / C-roll)
a topic, a talking-head video, or a still photo→fully generated film; talking-head re-styled with face/lip-sync preserved; photo anchored as a photographic sticker with optional voice cloning
Voice cloning (bytedance/seed-audio-1.0) processes a real person's voice via Atlas CloudLocal ffmpeg assembly & overlays
generated clips, narration, music and captions→final.mp4 with concatenated clips, music ducked under VO, burned-in captions and watermark
Requires local ffmpeg/ffprobe and Python 3 + Pillow for caption/watermark overlays
04Who is it for? When not to use it?
Good for
- Creators and marketers using DeepSeek Harness or another coding agent who need editorial-style explainer/ad videos without hand-editing them
- Video producers and brand teams that already have talking-head footage or product shots and want the Vox collage aesthetic
Not for
- All image, video, voice and music generation runs through the Atlas Cloud API — you need an Atlas Cloud API key and network access, and model usage is billed against your Atlas Cloud account.
05Compatibility, maintenance and safety notes
- All image, video, voice and music generation runs through the Atlas Cloud API — you need an Atlas Cloud API key and network access, and model usage is billed against your Atlas Cloud account.
- Model IDs on Atlas Cloud drift over time; the skill fetches the live model list before every run, and the model table is only verified on Atlas Cloud.
- Final assembly and caption/watermark overlays depend on locally installed ffmpeg + ffprobe and Python 3 with Pillow; the skill cannot produce the final MP4 without them.
MIT · actively maintained (last push 2026-08-11, no tagged releases yet)
06Frequently asked questions
How do I use Vox Director with DeepSeek Harness — native or MCP?
Neither — it is an agent skill, not an MCP server or native runtime. The README describes it as usable by any coding agent that can read a workflow and run scripts: clone it into your skills directory (Claude Code auto-discovers it) or install the packaged .skill file; other agents read AGENTS.md → SKILL.md. The README does not mention DeepSeek Harness specifically.
What do I need before installing?
A coding agent (Claude Code, Codex, or similar), an Atlas Cloud API key, ffmpeg + ffprobe, and Python 3 with Pillow for caption/watermark overlays.
Where do my data and requests go?
All generation — keyframes, animation, narration, music — is sent to the Atlas Cloud API (api.atlascloud.ai), including a live model-list fetch before each run. Final assembly happens locally with ffmpeg, writing output to out/<project>/final.mp4.
How much control do I keep over the video?
Two human decision gates: you approve the beat map (narrative arc) and pick the visual style from a bake-off of 3–4 themes; everything after that is automated.
07Related DSH workflows
dsh-voice-ai-girlfriend
by beiyege-01
Voice AI girlfriend for DeepSeek Harness — Whisper voice input, voice cloning, streaming TTS and a digital-human avatar with interrupt mode.
dsh-plugin-tts
by 1624318455
Edge TTS voice plugin for DeepSeek Harness: read assistant replies aloud, auto-read toggle, voice settings panel (free, no API key)
dsh-ears
by wiziscool
Voice input plugin for DeepSeek Harness (dsh): Supports voice input plugins with polishing and multiple backends.
dsh-speak
by alan2z
Make your DeepSeek Harness speak — voice announcements for agent activity.
08Data and sources
usable by any coding agent (Claude Code, Codex, etc.). You give it a one-line topic; it gives you an `mp4`.
This is an **agent skill** — it works with any coding agent that can read a workflow and run scripts (Claude Code, Codex…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.