Heygen Avatar API

Heygen Avatar 4 via fal.ai. Animate a portrait with prompt-driven speech or an audio track, with optional background and captions. Costs 2 credits per second of output video: an estimate is held at submission and settled to the actual duration when the job completes. Integrate this model via REST with endpoint docs, parameters, and code examples.

Compare video models Use cases

Video Generation

Img2Vid

Audio

Credit Cost

2 credits/sec

Type

Video

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/heygen-avatar/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/heygen-avatar.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`image` required	url	URL of the portrait image to animate	-
`prompt`	string	Text the avatar will speak. Required unless audio_url is provided.	-
`voice`	enum	Name of the voice to use for the avatar. Ignored when audio_url is provided. `Warm Pro NarratorChill BrianIvyJohn DoeMonika Sogam`+97 more	`Ivy`
`talking_style`	enum	stable for minimal movement, expressive for animated motion `stableexpressive`	`stable`
`expressionHappy`	boolean	Set true to add a "happy" facial expression. (Currently the only supported expression.)	`false`
`backgroundType`	enum	Background source: "none" leaves the avatar background intact; "color"/"image"/"video" replaces it via backgroundValue. `nonecolorimagevideo`	`none`
`backgroundValue`	string	Hex color for type=color, URL for type=image/video. Ignored when type=none.	-
`audio_url`	url	URL of an audio file for lip-sync. When provided, overrides prompt and voice. Billing holds a 60-second deposit (120 credits) up front, then settles to 2 credits per second of the actual output video on completion. The difference is refunded automatically.	-
`resolution`	enum	Output resolution preset `360p480p540p720p1080p`	`720p`
`aspect_ratio`	enum	Output video aspect ratio: 16:9 landscape, 9:16 portrait, or 1:1 square `16:99:161:1`	`16:9`
`caption`	boolean	Overlay generated captions on the output video	`false`

Supported Aspect Ratios

16:9

9:16

1:1

Example Outputs

Real outputs generated by this model

View Details

a thrilling action sequence of a woman trying to find her favorite candy. The candy wrapper is purple with a pixelated dragon and reads "Pixel Dojo". The woman says "Gotta have that pixel dojo candy. with over 60 ai tools, it's basically zero calories."

0 credits

View Details

Gotta have that pixel dojo candy. with over 60 ai tools, it is basically zero calories.

14 credits

72.3s

Code Examples

Portrait → talking video — copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/heygen-avatar/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://...",
    "prompt": "Hello from Heygen",
    "voice": "Ivy"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 10,
  "creditsRemaining": 95,
  "expiresAt": "2026-07-18T05:20:33Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "video": "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.mp4"
  },
  "creditCost": 10,
  "expiresAt": "2026-07-18T05:20:33Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits