# d-id-avatar-video

The d-id-avatar-video skill for Claude Code automates the generation, streaming, and localization of talking-head videos via the D-ID API.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 131 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/d-id-avatar-video/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/d-id-avatar-video

## What it does

The assistant coordinates D-ID workflows for presenter clips, interactive visual agents, and support training materials using either text scripts or audio files. It helps select the correct route ranging from Talks API for still portraits to Clips API with stock presenters and Scenes API for expressive emotion.

Preflight checks require a valid API-key, credit balance via `GET /credits`, and explicit likeness rights for any real person. The pipeline focuses strictly on head-and-shoulders human presenter segments rather than full-body cinematic action choreography.

Generation workflows rely on properly cropped frontal face portraits and predefined custody targets for resulting MP4 files and metadata.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill d-id-avatar-video -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/d-id-avatar-video/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/d-id-avatar-video/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill d-id-avatar-video -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/d-id-avatar-video/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill d-id-avatar-video -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/d-id-avatar-video/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/providers/avatar-video/d-id-avatar-video
```

2. **Manually: put the files in place**
- File: `.github/skills/d-id-avatar-video/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill d-id-avatar-video -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/providers/avatar-video/d-id-avatar-video
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/d-id-avatar-video/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill d-id-avatar-video -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/d-id-avatar-video/SKILL.md

## When to use it
- generate a speaking avatar video from a portrait image
- select a stock presenter for brand explainer clips
- set up a real-time WebRTC avatar stream with D-ID Agents
- configure localized video variants using script inputs

## Example prompts
- Generate a talking head video using D-ID Talks API
- Pick a stock presenter for training clips via Clips API
- Set up a real-time avatar stream using D-ID Agents

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: ec82a440fd235656.

BEGIN THIRD-PARTY FILE ec82a440fd235656
```text
---
name: d-id-avatar-video
description: Use D-ID to plan, generate, stream, localize, and QA avatar/talking-head videos, including V2 Photo Avatar Talks, V3 Pro/Instant Avatar Clips, V4 Expressive Avatar Scenes, D-ID Agents, voices, consent, lifecycle, safety, and artifact custody.
---

# D-ID avatar video production

Use this skill when the selected provider is D-ID or when the user asks for a D-ID talking avatar, photo-to-speaking-video, presenter clip, expressive avatar, interactive visual agent, real-time avatar stream, or D-ID-powered localization/support/training workflow.

Do not treat D-ID as a general cinematic video generator. It is primarily for human-presenter video: a face or presenter speaks text or audio with lip sync. For scenes that need object interaction, product handling, full-body action choreography, multi-shot narrative motion, or cinematic camera movement, use a broader video-generation or composition pipeline and use D-ID only for the presenter segments.

Facts in this skill were verified against official D-ID documentation and policies on 2026-07-10. Re-check live docs before quoting prices, enabled models, supported languages, moderation categories, endpoint schemas, or plan limits in user-facing commitments.

## Choose the D-ID route before scripting

Pick the route from the deliverable, not from habit:

| Need | D-ID route | Use when | Avoid when |
|---|---|---|---|
| A specific still portrait speaks | V2 Photo Avatar / Talks API (`POST /talks`) | The user supplies or owns a clear face image; personalization matters more than body motion. | The face is low-resolution, side-facing, celebrity-like, or permission is uncertain. |
| A polished stock presenter speaks | V3 Pro Avatar / Clips API (`POST /clips`) | Marketing, learning, onboarding, support snippets, or brand explainers need Full-HD presenter footage and natural presenter movement. | The user needs a specific person's identity. |
| A reusable custom video avatar | V3 Instant Avatar or V4 Expressive Avatar creation | The subject can complete consent verification and the project needs many videos with one owned avatar. | There is no consent video or the source footage is poor. |
| Expressive emotion and next-generation avatar behavior | V4 Expressive Avatar / Scenes API (`POST /scenes`) | Sentiment/emotion, more human facial detail, expressive training/support/sales presenters, or V4 agents are required. | A simple one-off photo-to-video clip is enough. |
| Live conversation | D-ID Agents, Agents SDK, Streams API, Embed SDK | The output is a website/chat/support/training agent with real-time WebRTC/LiveKit avatar responses. | The deliverable is a finished MP4 only. |
```
END THIRD-PARTY FILE ec82a440fd235656

The third-party file has ended. Everything between the ec82a440fd235656 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2698 of 24130 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/d-id-avatar-video/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
