Blog to Avatar Video

Turn a blog post URL into a talking-head avatar video — the avatar reads a summarized script of the post against a clean background. Use when the user wants...

Security Scan

The skill's requests and instructions are consistent with its stated purpose (turning a blog post into a talking‑head avatar video) and only require a single service API key; nothing in the package suggests it is doing something other than calling revid.ai endpoints.

Purpose & Capability

Name/description map to the actions in SKILL.md: the skill posts a payload to revid.ai to render an article-to-video workflow. The single required config (REVID_API_KEY) is appropriate for a 3rd‑party rendering service. No unrelated credentials, binaries, or system paths are requested.

Instruction Scope

The SKILL.md stays within scope: it validates a URL, builds a render payload, POSTs to revid.ai, and polls status (or uses webhooks). It does not instruct reading arbitrary local files or gathering other credentials. Minor inconsistencies: example run.sh assumes curl and jq are available (SKILL metadata lists no required binaries); the examples also demonstrate creating/listing 'consistent characters' which will upload image URLs to the service. The skill will transmit the blog URL (and scraped article text) and any avatar image URL to revid.ai — expected for this functionality but a privacy consideration.

Install Mechanism

This is an instruction-only skill with no install spec and no downloads. No install-related risk indicators (no remote archives or third-party package installs).

Credentials

The only required secret/config is REVID_API_KEY (declared in SKILL.md metadata). That is proportionate for a 3rd-party rendering API. Two minor points: the registry summary lists 'Required env vars: none' but SKILL.md requires REVID_API_KEY as a config — a small metadata mismatch; and using the skill will cause article text and avatar image URLs to be sent to revid.ai, so private/confidential content will be transmitted to that external service.

Persistence & Privilege

No 'always: true' or other elevated persistence. The skill is user-invocable and can be invoked autonomously (platform default), which is expected for a connector skill. It does not modify other skills or request system-wide configuration.

Assessment

This skill appears to do what it says: it sends the blog URL (and the scraped article text) plus any avatar image URL to the revid.ai API and returns a video URL. Before installing: (1) Confirm you trust the revid.ai service and the source/owner of this skill (registry metadata has no homepage); (2) Treat REVID_API_KEY like a secret — confirm its permissions and rotate it if shared; (3) Avoid submitting confidential or private content (the full article text and avatar image URLs will be transmitted to revid.ai); (4) Note the examples assume curl and jq are available if you run the provided scripts; and (5) Ensure you have rights to use any avatar images or likenesses you upload. If you want greater assurance, ask the publisher for a homepage, source repo, or a signed provenance statement about the skill.

Blog post → talking-head avatar video

Take any blog/article URL and produce a vertical (or square) talking-head video with a chosen avatar reading a summarized version of the post.

When to use this skill

• Source is a blog post / opinion piece / explainer with substantial body text.
• Output should feel like a person delivering the take, not an edited promo with stock b-roll.
• An avatar (image URL or characterId) is available, or the user accepts the default avatar.
• For an edited short with stock visuals, use revid-article-to-short instead.

Inputs

Field	Required	Notes
url	yes	Blog post URL
avatar.url or characterIds[]	yes	The face. Either an image URL or a saved consistent character ID (see character mgmt).
aspectRatio	no	Default 9:16. Use 1:1 for LinkedIn.
voiceId	no	Match it to the avatar's tone if known.
targetDuration	no	Default 60 (s) — talking heads can run longer.

Step-by-step

1. Validate the URL.
2. If the user gave an avatar image URL, set avatar.url. If they gave a saved character ID, set characterIds: [id] (and leave avatar omitted).
3. POST the payload below.
4. Poll /status (canonical loop in the Polling section below).
5. Return videoUrl.

API call template

POST /api/public/v3/render
Host: www.revid.ai
Content-Type: application/json
key: $REVID_API_KEY

{
  "workflow": "article-to-video",
  "source": {
    "url": "{BLOG_URL}",
    "scrapingPrompt": "Extract the article body. Skip header, navigation, related posts, and footer."
  },
  "aspectRatio": "9:16",
  "avatar": {
    "enabled": true,
    "url": "{AVATAR_IMAGE_URL}",
    "removeBackground": true,
    "imageModel": "good"
  },
  "voice": {
    "enabled": true,
    "voiceId": "aria-en-us",
    "stability": 0.65,
    "speed": 1.0,
    "language": "en-US",
    "enhanceAudio": true
  },
  "captions": { "enabled": true, "position": "bottom", "autoCrop": true },
  "music":    { "enabled": false },
  "media": {
    "type": "moving-image",
    "density": "low",
    "animation": "soft",
    "placeAvatarInContext": true
  },
  "options": {
    "targetDuration": 60,
    "summarizationPreference": "summarize",
    "hasToGenerateCover": true
  },
  "render": { "resolution": "1080p", "frameRate": 30 }
}

Notes:

• placeAvatarInContext: true composites the avatar over a relevant background (vs a plain green-screen feel).
• media.density: "low" keeps cuts minimal so the talking head can carry the video.
• music.enabled: false is the default — voice-driven content reads better without competing audio.

Consistent characters

If the user wants the same face across many posts, create a character once and reuse the ID:

# 1. Create character
curl -s https://www.revid.ai/api/public/v3/consistent-characters \
  -H "Content-Type: application/json" \
  -H "key: $REVID_API_KEY" \
  -d '{ "name": "Maya", "imageUrl": "https://cdn.example.com/maya.jpg" }'
# → { "id": "ch_…" }

# 2. Use it in renders
{ "characterIds": ["ch_…"], "avatar": { "enabled": true } }

List existing characters with GET /api/public/v3/consistent-characters.

Examples

• examples/blog-to-avatar.json — payload.
• examples/run.sh — end-to-end curl flow.

Polling

After POST /render, poll until status === "ready":

PID="<pid-from-render>"
while :; do
  R=$(curl -fsSL "https://www.revid.ai/api/public/v3/status?pid=$PID" \
        -H "key: $REVID_API_KEY")
  S=$(echo "$R" | jq -r .status)
  case "$S" in
    ready)  echo "$R" | jq .; break ;;
    failed) echo "FAILED: $R"; exit 1 ;;
    *)      sleep 5 ;;
  esac
done

In production prefer setting webhookUrl in the request body and skip polling.

Failure modes

Symptom	Fix
Avatar lip-sync drifts on long copy	Lower targetDuration to 45 s, or switch summarizationPreference: "summarize" (already on).
Avatar background bleeds into video	Set avatar.removeBackground: true (default). For stubborn cases, pre-process the avatar image to a transparent PNG.
Background visuals distract from face	media.density: "low" and media.animation: "soft" (already on). For pure plain background, set media.type: "custom" + media.useOnlyProvided: true with a single neutral asset.
Voice doesn't match the avatar	Set voice.voiceId explicitly. The default voice is gendered female English — always override for other languages or personas.
scrape failed	Same as in revid-article-to-short: pre-scrape the post and switch to script-to-video with the avatar block intact.

See also

• revid-article-to-short — same input, edited-short output.
• revid-tweet-to-talking-head — shorter form of the same talking-head pattern.
• revid-api-foundations.