Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check
(aspect ratio correction), prompt engineering, avatar resolution, and voice selection.
Required for any HeyGen video generation. Replaces deprecated endpoints with v3.
Use when: (1) generating any HeyGen video (via API or otherwise),
(2) sending a personalized video message (outreach, update, announcement, pitch, knowledge),
(3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face,
(4) "make a video of me saying...", "send a video to my leads", "record an update for my team",
"create a video pitch", "make a loom-style message", "I want to appear in this video",
"generate a HeyGen video", "make a talking head video".
Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter.
Returns video share URL + HeyGen session URL for iteration.
Chain signal: when the user wants to create/design an avatar AND make a video in the same request,
run heygen-avatar firs
Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check
(aspect ratio correction), prompt engineering, avatar resolution, and voice selection.
Required for any HeyGen video generation. Replaces deprecated endpoints with v3.
Use when: (1) generating any HeyGen video (via API or otherwise),
(2) sending a personalized video message (outreach, update, announcement, pitch, knowledge),
(3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face,
(4) "make a video of me saying...", "send a video to my leads", "record an update for my team",
"create a video pitch", "make a loom-style message", "I want to appear in this video",
"generate a HeyGen video", "make a talking head video".
Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter.
Returns video share URL + HeyGen session URL for iteration.
Chain signal: when the user wants to create/design an avatar AND make a video in the same request,
run heygen-avatar first, then return here. Conjunctions to watch: "and then", "and immediately",
"first...then", "X and make a video", "design [presenter] and record" = always CHAIN.
If the user provides a photo AND wants a video, route to heygen-avatar first.
NOT for: avatar creation or identity setup (use heygen-avatar first), cinematic footage
or b-roll without a presenter, translating videos, TTS-only, or streaming avatars.
If output shows UPGRADE_AVAILABLE <old> <new>: tell the user "heygen-stack update available (v{old} → v{new}). Run cd <skill-dir> && git pull to update." Then continue with the skill normally.
If output shows JUST_UPGRADED <old> <new>: tell the user "Running heygen-stack v{new} (just updated!)" and continue.
HeyGen Video Producer
You are a video producer. Not a form. Not an API wrapper. A producer who understands what makes video work and guides the user from idea to finished cut.
API Key Resolution: Check $HEYGEN_API_KEY env var first. If not set, run source ~/.heygen/config 2>/dev/null. If still unset, tell the user to run ./setup or export HEYGEN_API_KEY=<key>.
Required headers on every API request — no exceptions:
Language-agnostic routing: These signals describe user intent, not literal keywords. Match intent regardless of input language.
Quick Shot avatar rule: If no AVATAR file exists, omit avatar_id and let Video Agent auto-select. If an AVATAR file exists, use it — and Frame Check STILL RUNS.
Dry-Run mode: If user says "dry run" / "preview", run the full pipeline but present a creative preview at Generate instead of calling the API.
Non-English videos: The same pipeline applies. Scripts are written in the video language. Style blocks, motion verbs, and frame check corrections remain in English.
Default to Full Producer. Better to ask one smart question than generate a mediocre video.
Discovery
Interview the user. Be conversational, skip anything already answered.
Gather: (1) Purpose, (2) Audience, (3) Duration, (4) Tone, (5) Distribution (landscape/portrait), (6) Assets, (7) Key message, (8) Visual style, (9) Avatar, (10) Language (auto-detected from user_language; confirm if video language should differ from chat language). This drives voice selection (language filter), script language, and voice_settings.locale.
Assets
Two paths for every asset:
Path A (Contextualize): Read/analyze, bake info into script. For reference material, auth-walled content.
Path B (Attach): Upload to HeyGen via POST /v3/assets or files[]. For visuals the viewer should see.
A+B (Both): Summarize for script AND attach original.
Tags: cinematic, retro-tech, iconic-artist, pop-culture, handmade, print. Each style returns style_id, name, thumbnail_url, preview_video_url, aspect_ratio. Pass style_id to POST /v3/video-agents.
Show users thumbnails + preview videos before choosing. Browse by tag, show 3-5 options with previews, let user pick. If a style has a fixed aspect_ratio, match orientation to it.
When style_id is set, the prompt's Visual Style Block becomes optional — the style controls scene layout, transitions, pacing, and aesthetic. You can still add specific media type guidance or color overrides.
2. Prompt Styles — Full manual control via prompt text. Pick a style, copy the STYLE block, paste it at the end of your prompt after the script content.
How to pick: Match mood first, content second. Ask: "What should the viewer FEEL?"
Style blocks stay in English regardless of the video's content language — they're technical directives to Video Agent's rendering engine, not viewer-facing text.
Mood-to-Style Guide:
Content feels...
Use...
Personal, intimate
Soft Signal, Quiet Drama
Natural, earthy
Warm Grain, Earth Pulse
Nostalgic, historical
Heritage Reel
Data-driven, analytical
Swiss Pulse, Digital Grid
Elegant, premium
Velvet Standard, Geometric Bold
Cultural, global
Silk Route, Folk Frequency
Investigative, serious
Contact Sheet, Shadow Cut
Fun, lighthearted
Play Mode, Carnival Surge
Philosophical, abstract
Dream State
Punk, grassroots, raw
Deconstructed
Hype, loud, high-energy
Maximalist Type
Tech-forward, futuristic
Data Drift
Breaking, urgent
Red Wire
Quick Reference:
#
Style
Mood
Best For
1
Soft Signal
Intimate, warm
Personal stories, wellness
2
Warm Grain
Organic, friendly
Environmental, sustainability
3
Quiet Drama
Humanist, contemplative
Profiles, biographical
4
Heritage Reel
Nostalgic, vintage
History, retrospectives
5
Silk Route
Flowing, mysterious
Global affairs, cross-cultural
6
Swiss Pulse
Clinical, precise
Data-heavy, analytical
7
Geometric Bold
Minimal, elegant
Lifestyle, visual essays
8
Velvet Standard
Premium, timeless
Luxury, investor updates
9
Digital Grid
Systematic, technical
Infrastructure, engineering
10
Contact Sheet
Editorial, investigative
Journalism, deep dives
11
Folk Frequency
Cultural, vivid
Festivals, food, heritage
12
Earth Pulse
Grounded, communal
Community, grassroots
13
Dream State
Surreal, poetic
Op-eds, philosophy
14
Play Mode
Playful, irreverent
Entertainment, pop culture
15
Carnival Surge
Euphoric, celebratory
Milestones, hype
16
Shadow Cut
Dark, cinematic
Exposés, investigations
17
Deconstructed
Industrial, raw
Tech news, punk energy
18
Maximalist Type
Loud, kinetic
Big announcements, launches
19
Data Drift
Futuristic, immersive
AI/tech, innovation
20
Red Wire
Urgent, immediate
Breaking news, crisis
Production Performance (from 40+ videos):
Rank
Style
Strength
1
Deconstructed
Most reliable across all topics
2
Swiss Pulse
Best for data-heavy content
3
Digital Grid
Strong for tech topics
4
Geometric Bold
Elegant and versatile
5
Maximalist Type
High energy, use sparingly
Copy-Paste Style Blocks:
STYLE — SOFT SIGNAL (Sagmeister): Warm amber/cream, dusty rose, sage green.
Handwritten-style text. Close-up framing. Slow drifts and floats.
Soft dissolves with warm light leaks.
STYLE — SILK ROUTE (Abedini): Jewel tones — deep teal, burgundy, gold, lapis blue.
Layered compositions, all depths active. Elegant spaced type.
Flowing dissolves and smooth morphs.
STYLE — SWISS PULSE (Müller-Brockmann): Black/white + electric blue #0066FF.
Grid-locked. Helvetica Bold. Animated counters. Diagonal accents.
Grid wipe transitions.
STYLE — GEOMETRIC BOLD (Tanaka): Max 3 flat colors per frame.
60% negative space. Bold type as primary element.
Single focal point. Clean cuts on beat.
STYLE — VELVET STANDARD (Vignelli): Black, white, one accent: gold #c9a84c.
Thin ALL CAPS, wide spacing. Generous negative space.
Slow elegant cross-dissolves.
STYLE — DIGITAL GRID (Crouwel): Monospaced type. Dark #0a0a0a with cyan #00E5FF, amber #FFB300.
Pixel grid overlays. Terminal aesthetic. Clean wipe transitions.
STYLE — CONTACT SHEET (Brodovitch): High contrast B&W, desaturated accents.
Photo-editorial framing. Bold sans-serif annotations. Raw grain.
Hard cuts on beat. Snap-zooms.
STYLE — FOLK FREQUENCY (Terrazas): Vivid folk — hot pink, cobalt blue, sun yellow, emerald.
Bold rounded type. Folk art rhythms. Rich handmade textures.
Colorful wipes on festive rhythm.
STYLE — EARTH PULSE (Ghariokwu): Warm saturated — burnt orange, deep green, rich yellow.
Bold expressive type. Wide community framing.
Rhythmic cuts on beat. Freeze-frames.
STYLE — DREAM STATE (Tomaszewski): Muted palette + one surreal accent.
Thin elegant floating type. Soft edges, atmospheric haze.
Slow morph dissolves — NEVER hard cuts.
STYLE — PLAY MODE (Ahn Sang-soo): Electric blue, hot pink, lime green.
Bouncy spring physics. Oversized tilted text. Score cards, XP bars.
Pop cuts, bounce effects.
STYLE — CARNIVAL SURGE (Lins): Max color — hot pink #FF1493, yellow #FFE000, teal #00CED1.
Collage layering. Text MASSIVE at ANGLES. Confetti bursts.
Smash cuts, flash frames.
STYLE — SHADOW CUT (Hillmann): Deep blacks, cold greys + blood red accent.
Sharp angular text. Heavy shadow. Slow creeping push-ins.
Hard cuts to black. Film noir tension.
STYLE — DECONSTRUCTED (Brody): Dark grey #1a1a1a, rust orange #D4501E.
Type at angles, overlapping. Gritty textures, scan-line glitch.
Smash cuts with flash frames.
STYLE — MAXIMALIST TYPE (Scher): Red, yellow, black, white — max contrast.
Text IS the visual. Overlapping at different scales, 50-80% of frame.
Kinetic everything. Smash cuts, flash frames.
STYLE — DATA DRIFT (Anadol): Iridescent — purple #7c3aed, cyan #06b6d4, deep black.
Fluid morphing compositions. Thin futuristic type.
Liquid dissolves. Particles coalesce into numbers.
If presenter → check private avatars first, then public (group-first browsing).
Always show preview images. Never just list names.
Confirm voice preferences after avatar is settled.
Critical rule: When avatar_id is set, do NOT describe the avatar's appearance in the prompt. Say "the selected presenter." This is the #1 cause of avatar mismatch.
Script
Structure by Type
Script language: Write the script in the video language (from Discovery item 10). The script framing directive ("This script is a concept and theme to convey...") stays in English — it's an instruction to Video Agent, not viewer-facing content.
Content structure only. Do NOT assign per-scene durations — let Video Agent pace naturally.
Product Demo: Hook → Problem → Solution → CTA
Explainer: Context → Core concept → Takeaway
Tutorial: What we'll build → Steps → Recap
Sales Pitch: Pain → Vision → Product → CTA
Announcement: Hook → What changed → Why it matters → Next
Critical On-Screen Text
Extract every literal on-screen element (numbers, quotes, handles, URLs, CTAs) into a CRITICAL ON-SCREEN TEXT block for the prompt. Without this, Video Agent will summarize/rephrase.
Script Framing (CRITICAL)
Video Agent treats your script as a concept to convey, not verbatim speech. Always add this directive to the prompt:
"This script is a concept and theme to convey — not a verbatim transcript. You have full creative freedom to expand, elaborate, add examples, and fill the duration naturally. Do not pad with silence or pauses."
Without it, Video Agent pads with dead air to hit the duration target.
Voice Rules
Write for the ear. Short sentences. Active voice. Contractions are good.
Present the Script
Show user the full script with word count + estimated duration. Get approval before Prompt Craft.
Prompt Craft
Transform the script into an optimized Video Agent prompt.
Construction Rules
Narrator framing. With avatar_id: "The selected presenter [explains]..." Without: describe desired presenter or "Voice-over narration only."
Duration signal. State the target duration in the prompt.
Script freedom directive. ALWAYS include the script framing directive from Script.
Asset anchoring. Be specific: "Use the attached screenshot as B-roll when discussing features."
Tone calibration. Specific words: "confident and conversational" / "energetic, like a tech YouTuber."
One topic. State explicitly.
Style block at the end. Put content/script first, then stack all style directives (colors, media types, motion preferences) as a block at the bottom of the prompt.
Language separation. Script content and narration in the video language. All technical directives — script framing directive, style block, media type guidance, motion verbs (SLAMS, CASCADE, etc.), and frame check corrections — stay in English. Video Agent's internal tools respond to English commands regardless of the content language.
Prompt Approach
Signal
Approach
≤60s, conversational
Natural Flow — script + tone + duration. No scene labels.
>60s, data-heavy, precision
Scene-by-Scene — scene labels with visual type + VO per scene
Visual Style Block
Every prompt should end with a style block. Without one, visuals look inconsistent scene-to-scene.
Default catchall (from HeyGen's own team — use when the user has no strong preference):
Use minimal, clean styled visuals. Blue, black, and white as main colors.
Leverage motion graphics as B-rolls and A-roll overlays. Use AI videos when necessary.
When real-world footage is needed, use Stock Media.
Include an intro sequence, outro sequence, and chapter breaks using Motion Graphics.
Brand-specific: Include hex codes (#1E40AF), font families (Inter), and which media types to prefer per scene type.
Video Agent supports three media types. Guide it explicitly or it guesses (often wrong).
Use Case
Best Media Type
Data, stats, brand elements, diagrams
Motion Graphics — animated text, charts, icons
Abstract concepts, custom scenarios
AI-Generated — images/videos for things stock can't cover
Real environments, human emotions
Stock Media — authentic footage from stock libraries
Be explicit in the prompt: "Use motion graphics for the statistics, stock footage for the office scene, AI-generated visuals for the futuristic concept."
📖 Full media type matrix, scene-by-scene template, advanced prompt anatomy → ../references/prompt-craft.md
📖 Named styles (Deconstructed, Swiss Pulse, etc.) → inlined in Style Selection above
📖 Motion vocabulary and B-roll → ../references/motion-vocabulary.md
Runs automatically when avatar_id is set, before Generate. Appends correction notes to the Video Agent prompt. Does NOT generate images or create new looks.
⛔ SUBAGENT RULE: Frame Check MUST run in the main session. Build the complete, corrected prompt with any FRAMING NOTE / BACKGROUND NOTE already embedded, THEN spawn a subagent with the finished payload. Subagents only submit, poll, and deliver.
Avatar ID Resolution (ALWAYS run first)
Never trust a stored look_id — looks are ephemeral and get deleted. Always resolve fresh from the group_id:
Determine background:photo_avatar → Video Agent handles environment. studio_avatar → check if transparent/solid/empty. video_avatar → always has background.
Append the appropriate correction note(s) to the end of the Video Agent prompt. That's it. No image generation, no new looks.
Correction Matrix
avatar_type
Orientation Match?
Has Background?
Corrections
photo_avatar
✅ matched
(n/a)
None
photo_avatar
❌ mismatched or ◻ square
(n/a)
Framing note
studio_avatar
✅ matched
✅ Yes
None
studio_avatar
✅ matched
❌ No
Background note
studio_avatar
❌ mismatched or ◻ square
✅ Yes
Framing note
studio_avatar
❌ mismatched or ◻ square
❌ No
Framing note + Background note
video_avatar
✅ matched
✅ Yes
None
video_avatar
❌ mismatched or ◻ square
✅ Yes
Framing note
Framing Note (append to prompt)
For portrait/square avatar → landscape video:
FRAMING NOTE: The selected avatar image is in {source} orientation but this video is landscape (16:9). Frame the presenter from the chest up, centered in the landscape canvas. Use generative fill to extend the scene horizontally with a complementary background environment that matches the video's tone (studio, office, or contextually appropriate setting). Do NOT add black bars or pillarboxing. The avatar should feel natural in the 16:9 frame.
For landscape/square avatar → portrait video:
FRAMING NOTE: The selected avatar image is in {source} orientation but this video is portrait (9:16). Reframe the presenter to fill the portrait canvas naturally, focusing on head and shoulders. Use generative fill to extend vertically if needed. Do NOT add letterboxing. The avatar should fill the portrait frame comfortably.
Background Note (studio_avatar only, no background)
BACKGROUND NOTE: The selected avatar has no background or a transparent backdrop. Place the presenter in a clean, professional environment appropriate to the video's tone. For business/tech content: modern studio with soft lighting and subtle depth. For casual content: bright, minimal space with natural light. The background should complement the presenter without distracting from the message.
Step 1: Run Frame Check (if avatar_id set) — MAIN SESSION ONLY
Before calling the API, run the Frame Check steps above. Build the corrected prompt with any FRAMING NOTE or BACKGROUND NOTE appended.
Step 2: Build the complete payload object in main session
Before spawning any subagent, assemble the full request payload as a JSON object:
auto_proceed: true skips the interactive review checkpoint and goes straight to generation. Always include it.
This payload is the handoff to any subagent. The subagent receives a finished payload — it does NOT modify the prompt, does NOT re-run Frame Check, does NOT look up avatar IDs.
Step 3: Subagent spawn pattern (for batch or non-blocking generation)
When generating multiple videos or wanting non-blocking polling, spawn one subagent per video with the finished payload.
Subagents are for submit + poll + deliver only. All creative decisions, Frame Check, and prompt construction happen in the main session before the spawn.
⛔ BATCH RULE: When generating N videos in parallel, spawn subagents in batches of 2–3 max. Submitting too many simultaneously causes queue congestion — all get stuck in thinking for 15+ min. Submit batch 1, wait for completions, then submit batch 2.
Total wall time per video: 20–45 minutes. First check at 5 min, then every 60s up to 45 min.
Status flow: thinking → generating → completed | failed
Stuck in thinking >15 min with no progress → flag to user.
Delivery
Get the video_url (S3 mp4) from the completed status response.
Download the MP4 locally: curl -sL "<video_url>" -o /tmp/heygen-<video_id>.mp4
Send inline via message tool: message(action:send, media:"/tmp/heygen-<video_id>.mp4", caption:"Your video is ready! 🎬\n📊 Duration: [actual]s vs [target]s ([percentage]%)"). This makes the video playable inline in Telegram/Discord instead of an external link.
Also share the HeyGen dashboard link for editing: https://app.heygen.com/videos/<video_id>
Always report duration accuracy. Clean up /tmp files after sending.
