From ai-business-skills
Manages AI avatar production pipeline with 3-tier tools, 4 workflows (single, translate, batch, hybrid), voice clone, anti-detection, and region-specific disclosure laws.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-business-skills:24-ai-avatar-production-globalThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Flagship skill of the AI Content cluster. Covers the full pipeline from zero to publish, voice clone, anti-detection, and region-specific disclosure law.
Flagship skill of the AI Content cluster. Covers the full pipeline from zero to publish, voice clone, anti-detection, and region-specific disclosure law.
An AI Avatar is a video that shows your face (or a stand-in) but uses AI-generated voice and motion. You provide one photo or a short selfie video; the AI produces a final video with natural-looking speech, gestures, and expressions. No filming crew, no studio, no actor required.
| Method | Requirement | Quality |
|---|---|---|
| Portrait photo | 1 forward-facing photo, clean background, 1024x1024+ | Medium — mouth less natural |
| Selfie video | 30s video, looking at the lens, speaking naturally | Good — better lipsync |
| Custom avatar | 2-5 min recording with teleprompter + lavalier mic | Excellent — near photo-real |
Minimum gear: Phone with HD front camera + lavalier mic (or headset mic).
| Tier | USD/month | Output |
|---|---|---|
| Free | $0 | 1-3 videos, watermark |
| Pro | $30-100 | 10-30 videos, no watermark |
| Enterprise | $200-500+ | 30+ videos, custom avatar, API |
Ask up to 4 questions before starting:
Based on the 4 answers, auto-select Tier + Workflow.
| Tier | Suggested tool | Price/month | Quality | Limit | Fits |
|---|---|---|---|---|---|
| Free | Captions Free, HeyGen Trial, D-ID Trial | $0 | 6/10 — watermark, limited duration | 1-5 videos, max 60s/video | Personal test, new freelancers |
| Pro | HeyGen Creator ($29), Synthesia Starter ($29), ElevenLabs Pro ($22) | $30-100 | 8/10 — no watermark, HD | 10-30 videos, max 5 min/video | SME, small agency, content creator |
| Enterprise | HeyGen Business ($89+), Synthesia Enterprise (custom) | $200-500+ | 9.5/10 — custom avatar, API, priority render | 30+ videos, unlimited | Large agency, large brand, e-learning |
Quick recommendations:
One video, end-to-end in 30-60 minutes.
| Step | Task | Tool | Time |
|---|---|---|---|
| 1. Script | 150-300 words for a 60s video | Skill 04-script-video-global | 10 min |
| 2. Voice | Generate or use voice clone | ElevenLabs / HeyGen Voice | 5 min |
| 3. Avatar | Pick stock avatar or upload your media | HeyGen / Synthesia / D-ID | 3 min |
| 4. Render | Combine voice + avatar, choose background, gestures | Tool from step 3 | 5-15 min (render) |
| 5. QA | QA Score 100 review (see section below) | Manual review | 5 min |
| 6. Publish | Export MP4 -> post to platform | Manual / Scheduler | 2 min |
[HOOK — 3s] Curiosity hook, frame the problem
[PROBLEM — 10s] Describe the customer pain
[SOLUTION — 25s] Your solution, 2-3 key points
[PROOF — 12s] Numbers, testimonial, result
[CTA — 10s] Concrete action: "Link in bio for..."
One source video -> many languages for global rollout. Use cases: DTC brand expanding markets, multi-language courses, multi-country agency work.
| Tool | Languages | Price | Notes |
|---|---|---|---|
| Rask AI | 130+ | $50/mo (Pro) | Best for translate today |
| HeyGen Translate | 40+ | Included Creator+ | Built-in, convenient |
| Synthesia Translate | 35+ | Included Enterprise | Best for e-learning |
Caveat: Tonal languages (Mandarin, Vietnamese, Thai) have weaker lipsync. Workaround: produce native voice clone + native avatar per language.
See full disclosure law per region in the variant files.
30 videos in 5 days — assembly-line process.
| Day | Task | Output | Tool |
|---|---|---|---|
| Day 1 | Script batch — write 10 scripts from template | 10 scripts (.md) | Skill 04-script-video-global + AI assist |
| Day 2 | Voice batch — render 10 audio files | 10 audio (.mp3) | ElevenLabs API |
| Day 3 | Avatar batch — upload audio + avatar, queue render | 10 videos rendering | HeyGen Batch / Synthesia |
| Day 4 | QA batch — review 10 videos, fix issues, re-render | 10 QA'd videos | Manual + QA Score |
| Day 5 | Publish batch — export, add captions, schedule | 10 videos published | Buffer / Later / Manual |
Repeat 3 weeks = 30 videos. Or scale Days 1-2 to 15 scripts/week.
| Tier | Tool combo | Monthly cost | Per-video cost |
|---|---|---|---|
| Free | HeyGen Trial + Captions Free | $0 (limited 3-5 videos) | $0 (watermark) |
| Pro | HeyGen Creator + ElevenLabs Pro | ~$51 | ~$1.70 |
| Enterprise | HeyGen Business + ElevenLabs Scale | ~$189 | ~$6.30 |
Real face for trust + AI body for speed.
Trust gain: Real face up front -> 20-35% more engagement than full-AI.
| Criterion | Requirement |
|---|---|
| Duration | 3-5 minutes |
| Quality | WAV/FLAC, 44.1kHz+, mono, quiet room |
| Script content | Phonetically varied passages (all vowels, hard consonants) |
| Emotion | Read normal, natural, not acted |
| Tool | Price | Quality | Notes |
|---|---|---|---|
| ElevenLabs | From $5/mo | 9/10 | Best overall, 30+ languages |
| HeyGen Voice | Included Creator+ | 6/10 | Convenient if using HeyGen |
| Resemble AI | From $99/mo | 7/10 | Strong API |
| PlayHT | From $39/mo | 7/10 | Good for narration |
MANDATORY before cloning anyone's voice.
VOICE USAGE CONSENT
I, [FULL NAME], consent to [COMPANY] using my voice for: [SPECIFIC PURPOSE].
Term: [X months / Until revoked]
Date: [YYYY-MM-DD]
Signature: _______________
Reference: See
references/voice-clone-prompts-global.md
Before recording / uploading photo or video for an AI avatar:
| Signal | Platforms flagging | Fix |
|---|---|---|
| Stiff face, no natural blinking | FB, IG | Use selfie video over photo; pick avatars with micro-expressions |
| Monotone voice, no natural pauses | TikTok, FB | Use voice clone (natural pacing) over default TTS |
| Fully static background | FB, IG | Add slight noise/grain, or use real-world background |
| Isolated motion (only mouth moves) | TikTok | Pick avatars with gesture (hands, head); use HeyGen v3+ |
| Metadata flagged as AI tool | YouTube (monetize) | Re-export through CapCut (strips metadata); add color grade |
CRITICAL: NEVER use AI avatars to impersonate real people without consent. This is illegal in most jurisdictions and grounds for permanent platform bans.
Disclosure laws differ dramatically by region. Pick the matching variant:
| Region | Variant file | Key law |
|---|---|---|
| US / Canada | variants/01-us.md | FTC Endorsement Guides (16 CFR Part 255), 2023 update |
| EU / EEA / UK | variants/02-eu.md | EU AI Act Article 50 (always disclose) + UCPD + GDPR |
| Southeast Asia | variants/03-sea.md | Per-country: ASAS (SG), AKARI (ID), DTI (PH), MCMC (MY), TH |
| Latin America | variants/04-latam.md | CONAR + LGPD (BR), PROFECO (MX), AAIP (AR), per-country |
ALWAYS read the matching variant BEFORE publishing AI avatar content in that region. Penalties range from warning to multi-thousand-USD fines per influencer (US) and can stack under EU AI Act + GDPR.
When in doubt, disclose. Disclosure is rarely penalized; non-disclosure can be.
"This video uses AI Avatar technology for visuals and voice."
Placement: video description, first 3 seconds on-screen text, OR platform "AI-generated" tag (where available — Meta, TikTok, YouTube all now support this).
| # | Criterion | Points | Description |
|---|---|---|---|
| 1 | Lipsync | /10 | Mouth tracks speech within 0.2s |
| 2 | Voice match | /10 | Voice sounds like the speaker (if clone) or natural (if TTS) |
| 3 | Visual quality | /10 | Sharp image, no artifacts, no blur |
| 4 | Background | /10 | Background suits context, no render glitches |
| 5 | Lighting | /10 | Even light, no harsh shadows, matches background |
| 6 | Gesture | /10 | Natural, no jitters, hand/head movement present |
| 7 | Script flow | /10 | Hook -> Problem -> Solution -> CTA |
| 8 | Disclosure | /10 | AI disclosure compliant with region (see variant) |
| 9 | Platform fit | /10 | Correct aspect ratio, duration, format for platform |
| 10 | CTA | /10 | Clear call-to-action, easy to execute |
| Tier | Score | Action |
|---|---|---|
| Excellent | 90-100 | Publish now |
| Good | 70-89 | Publish, note improvements for next round |
| Needs fix | 50-69 | Fix items scoring under 7, then re-render |
| Redo | <50 | Rebuild from script + voice + avatar |
# AI Avatar Video — [Title] | [Region variant] | [Date]
1. Workflow used: [Single / Translate / Batch / Hybrid]
2. Script: [Content, 150-300 words]
3. Voice: [Tool] — [Voice ID / clone name] — Consent: [Yes / N/A]
4. Avatar: [Tool] — [Avatar ID / custom]
5. QA Score: [X]/100 (10 criteria)
6. Disclosure (per region variant): [Text + placement]
7. Publish: [Platform] — [Aspect ratio] — [Link]
25-voice-clone-podcast-global — voice clone deep-dive + podcast pipeline04-script-video-global — script writing for AI avatar26-thought-leadership-content-global — content strategy for personal brandreferences/ai-video-disclosure-global — full legal referencereferences/voice-clone-prompts-global — voice clone training promptsGlobal Skill 24 (AI Avatar Production) | Over Powers Agency | v1.0.0
npx claudepluginhub minhnv0807/ai-business-skills --plugin ai-business-skillsPipeline for AI avatar video production: single avatar, translation, batch, and hybrid real+AI workflows. Tools: HeyGen, Synthesia, ElevenLabs, Captions, Rask AI, Vbee. Includes voice cloning, anti-detection, and VN ethics compliance.
Generates marketing videos using AI generation models, AI avatars (HeyGen, Synthesia), and programmatic frameworks (Remotion, Hyperframes). Supports product demos, explainers, and social clips.
Creates video content using AI generation models, avatars, and programmatic frameworks like Remotion and HeyGen. Handles product demos, explainers, and social clips.