by HeyGen

A portrait speaks your recording at 1080p or 2K with gestures that follow the script, up to 10 minutes

heygen/avatar-6/talking-avatar
  • Up to 2K
  • AI Avatar

About HeyGen Avatar 6

A portrait speaks your recording at 1080p or 2K with gestures that follow the script, up to 10 minutes.

Call it with the model name heygen/avatar-6/talking-avatar on POST /jobs/createTask, from $0.12.

Introduction

Native 1080p and 2K talking portraits from photo and speech

heygen/avatar-6/talking-avatar animates a single portrait image and spoken audio recording into an asynchronous 1080p or 2K MP4. HeyGen says Avatar 6 analyzes roughly 30 seconds of surrounding speech context so posture changes, hand movements, and facial nuance follow phrasing rather than repeating short motion loops.

Each input carries a clear role: image_url sets the speaker's identity, wardrobe, lighting, and scene; audio_url supplies the spoken words and clip length (1 to 600 seconds); and optional prompt, expressiveness, and reference_video_urls refine physical delivery.

Parameters

ParameterRequiredType & LimitsPurpose
audio_urlYesURI (MP3 or WAV, 1–600s)Spoken audio track driving lip sync, gesture timing, and final clip duration.
promptNoString (1–1,200 chars)Plain-language cues for expression, gaze, head tilts, posture, and hand movement.
resolutionNo1080p (default) or 2kOutput tier: 1080p (1080px short edge) or 2k (1620px short edge); sets the per-second rate.
widthNoEven integer (256–3840)Optional exact output width in pixels; must be paired with height.
heightNoEven integer (256–3840)Optional exact output height in pixels; must be paired with width.

Expressiveness and text direction

Leave expressiveness at default when you want Avatar 6 to match gesture energy to spoken emphasis. Switch to less for newsroom briefings, quiet late-night monologues, or tight close-ups where minimal torso movement reads cleaner.

Using reference_video_urls

Realistic human reference videos require dedicated consent approval and are rejected on standard workspaces.

Verified live run and sample notes

In our 2026-11-19 live test, a 3.79-second portrait audio track at 1080p finished in roughly 35 seconds and returned a 1088×1632 MP4 preserving portrait proportions. Because generation is asynchronous, use status polling or webhooks in production pipelines.

  • Champagne studio whisper (1080p): Soft studio lighting on an off-shoulder champagne satin portrait paired with a quiet close-range line, showing warm eye contact and gentle head tilts aligned with speech.
  • Velvet balcony monologue (2k): Dark velvet off-shoulder evening portrait on a candlelit night balcony rendered at 1620px short edge, preserving fabric sheen, steady blinks, and calm posture shifts.

Choosing between Avatar 6, Avatar 6 Turbo, and Avatar IV

  • Pick HeyGen Avatar 6 when close-up facial detail, 2K clarity, and unprompted micro-expressions are your primary goals.
  • Pick HeyGen Avatar 6 Turbo when running bulk personalized outreach, high-volume localized variants, or rapid script drafts where quicker turnaround and lower per-second rates matter more than fine close-up nuance.
  • Pick HeyGen Avatar IV if you specifically need background_image_url scene swapping or three-level (low/medium/high) expression controls at up to 1080p.

Consent, likeness rights, and permitted inputs

Verify rights to both image_url and audio_url prior to submission, and download completed MP4 outputs promptly once verified.

Request parameters

ParameterRequiredDescription
audio_urlYesThe voice or music track to use.
expressivenessNoHow much the face and head move: low (the default), medium or high. default · less · Default: default
heightNoOutput height in pixels for a custom size. Available limits depend on the model. ≥ 256 · ≤ 3840
image_urlYesThe picture to start from.
promptNoDescribe what you want to make.
reference_video_urlsNoClips whose motion, camera or style the result should follow.
resolutionNoChoose an available output size. 1080p · 2k · Default: 1080p
widthNoOutput width in pixels for a custom size. Available limits depend on the model. ≥ 256 · ≤ 3840

Pricing

Prices are in USD and charged to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
resolution 1080p$0.12
resolution 2K$0.174

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

API quick start

Call the HeyGen Avatar 6 API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls are billed in USD from your PopNow balance.
  2. Send the request. POST /jobs/createTask with model heygen/avatar-6/talking-avatar and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "heygen/avatar-6/talking-avatar",
  "input": {
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3",
    "resolution": "1080p",
    "expressiveness": "default"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

HeyGen Avatar 6 API questions

How much does the HeyGen Avatar 6 API cost?

HeyGen Avatar 6 costs $0.12 per second. Prices by option: 1080p $0.12 per second, 2K $0.174 per second. API usage is charged in USD to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for HeyGen Avatar 6 in the API?

Put heygen/avatar-6/talking-avatar for AI Avatar in the model field of POST /jobs/createTask.

What inputs does the HeyGen Avatar 6 API require?

Every request requires a portrait image in image_url and a spoken audio file in audio_url. Accepted portraits are JPEG, PNG, or WebP files up to 32 MB, and audio must be an MP3 or WAV recording between 1 and 600 seconds. Optional controls add prompt, resolution, expressiveness, reference_video_urls, and paired width and height.

How does Avatar 6 differ from Avatar 6 Turbo and Avatar IV?

Avatar 6 prioritizes detailed 1080p and 2K facial fidelity and nuanced phrase-aware motion, while [HeyGen Avatar 6 Turbo](/models/heygen-avatar-6-turbo) targets quicker turnaround and lower per-second rates for high-volume runs. Compared with [HeyGen Avatar IV](/models/heygen-avatar-iv), Avatar 6 adds native 2K output, custom pixel dimensions, and optional video motion references, whereas Avatar IV tops out at 1080p and includes background image swapping.

Can a text prompt replace the speech audio recording?

No, audio_url is mandatory because HeyGen Avatar 6 animates directly from spoken audio. The optional prompt field (up to 1,200 characters) directs expression, eye contact, posture, and gesture style without generating speech. Record or synthesize your voice track beforehand, then use prompt to refine physical delivery.

How long does rendering take, and what resolution came out in testing?

In our 2026-11-19 live run, a 3.79-second portrait audio clip at 1080p completed in about 35 seconds and returned a 1088×1632 MP4. Longer scripts and 2K jobs take proportionally more compute time because the endpoint runs asynchronously. Poll the task status or use webhooks rather than holding an open synchronous request.

What are the limits of the HeyGen Avatar 6 API?

Resolutions: 1080p · 2K; Reference videos: 1; Prompt length (characters): 1,200. Requests outside these limits are rejected before anything is charged.

Can I try HeyGen Avatar 6 without writing code?

Run HeyGen Avatar 6 in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All HeyGen models

More about HeyGen Avatar 6