HeyGen Avatar 4 Image to Video

Name: HeyGen Avatar 4 Image to Video
Price: 0.5 USD
Availability: InStock
Author: HeyGen

heygen/heygen-avatar4/image-to-video

Heygen Avatar4 is HeyGen's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Use in agent Get API key

Base price: $0.50USD / run
Execution: async
Model type: video
Input fields: 7

Production route

Try the model

Playground

Open playground

Input

Prompt(string)

The text the avatar will speak

Image Url(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to animate. The image should contain a clear face.

This field is required.

Audio Url(string)

URL of an audio file for the avatar to lip-sync to. When provided, overrides prompt and voice.

Aspect Ratio(string)

Output aspect ratio. Omit to keep the source aspect ratio (falls back to 16:9 when it cannot be read). Allowed values: 16:9, 9:16, 4:5, 5:4, 1:1.

Voice(string)

The voice ID to use for the avatar.

Resolution(string)

Video resolution preset. Allowed values: 360p, 480p, 540p, 720p, 1080p.

Talking Style(string)

Talking style: 'stable' for minimal movement, 'expressive' for more animation. Allowed values: stable, expressive.

OutputExample

Open original

Examples

Select an example to load its inputs and result into the playground.

Model card

Specifications

Pricing

Base price: $0.50 / run

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: HeyGen
Model ID: heygen/heygen-avatar4/image-to-video
Execution: async
Base URL: https://api.sandbase.ai
API: Unified Run API
Endpoint: /v1/run

API README

HeyGen Avatar 4 Image to Video

HeyGen Avatar 4: turn a single photo into a talking presenter, driven by a script or an audio track.

Fields

Field	Type	Default	Notes
`prompt`	string	—	Script to speak.
`image`	image URL, required	—	Photo of the presenter. JPEG, PNG, or WebP URL.
`audio`	audio URL	—	Optional voice track.
`aspect_ratio`	`16:9` / `9:16` / `4:5` / `5:4` / `1:1`	—	Output frame shape.
`voice`	string	`Melissa`	Voice for the script.
`resolution`	`360p` / `480p` / `540p` / `720p` / `1080p`	`720p`	Video resolution preset.
`talking_style`	`stable` / `expressive`	`stable`	`expressive` adds more head and hand motion.

Billing

$0.10 per output second; length follows the audio or the spoken script. The quote before submission assumes 5 seconds.

Output	Price
5s	$0.50
30s	$3.00
60s	$6.00

Failed runs are not charged.

Prompting

Use a front-facing photo with the face clearly visible.

Also on SandBase

Related: heygen/avatar5/digital-twin.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

heygen/heygen-avatar4/image-to-video

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "heygen/heygen-avatar4/image-to-video",
  "image": "https://v3b.fal.media/files/b/0a90062c/A7EIviZqNxZ2HAs0yHeZ6_77a05b99-8588-4ffc-90aa-be7f9d34e9d3.png",
  "voice": "Melissa",
  "prompt": "Hey friends! Welcome to the GPU force podcast and today we are going to discuss about the rising GPU cost!",
  "resolution": "720p",
  "talking_style": "stable"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
HeyGen Avatar 4 Image to VideoThis model `HeyGen`	Video	$0.50 / run	Feb 23, 2026
HeyGen Avatar 5 Digital Twin `HeyGen`	Video	$0.60 / run	May 20, 2026
HeyGen Video Agent V3 `HeyGen`	Video	$1.02 / run	Apr 16, 2026
HeyGen Lipsync Precision `HeyGen`	Video	$0.50 / run	Apr 16, 2026
HeyGen Lipsync Speed `HeyGen`	Video	$0.25 / run	Apr 16, 2026

Questions

FAQ

How do I call HeyGen Avatar 4 Image to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "heygen/heygen-avatar4/image-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate HeyGen account?

No. One SandBase API key and balance gives you access to HeyGen Avatar 4 Image to Video and the other models in the catalog; you do not need to sign up with HeyGen separately.