HeyGen Avatar 6

HeyGen Avatar 6 is an audio-driven avatar video model that animates a HeyGen avatar, a single photo, or a reference video of an animated or illustrated character. It generates gestures and facial expressions that match what is being said, with accurate lip sync and native 2K output, and a motion prompt can direct gestures, posture and camera. It suits presenter, training and product videos where natural motion matters.
Complete technical specification for integration
Ready-to-use code snippets for common workflows
Step-by-step tutorials for advanced use cases
API Options
Platform-level options for task execution and delivery.
taskType
stringrequiredvalue: videoInferenceIdentifier for the type of task being performed.
taskUUID
stringrequiredUUID v4UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.
outputType
stringdefault: URLVideo output type.
Allowed values1 value
outputFormat
stringdefault: MP4Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.
- `MP4`: Widely supported video container (H.264), recommended for general use.
- `WEBM`: Optimized for web delivery.
- `MOV`: QuickTime format, common in professional workflows (Apple ecosystem).
Allowed values3 values
outputQuality
integermin: 20max: 99default: 95Compression quality of the output. Higher values preserve quality but increase file size.
webhookURL
stringuriWebhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.
Learn more1 resource
- WebhooksPLATFORM
- Webhooks
deliveryMethod
stringdefault: asyncDetermines how the API delivers task results.
Allowed values2 values
- Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.
Learn more1 resource
- Task PollingPLATFORM
uploadEndpoint
stringuriSpecifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.
Common use cases:
- Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- CDN integration: Upload to content delivery networks for immediate distribution.
// S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpgThe content data will be sent as the request body to the specified URL when generation is complete.
safety
objectContent safety checking configuration for video generation.
Properties2 properties
safety»checkContentcheckContent
booleanEnable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.
safety»modemode
stringdefault: fastSafety checking mode for video generation.
Allowed values2 values
- Checks key frames.
- Checks all frames.
ttl
integermin: 60Time-to-live (TTL) in seconds for generated content. Only applies when
outputTypeisURL.
includeCost
booleanInclude task cost in the response.
numberResults
integermin: 1max: 4default: 1Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
Inputs
Input resources for the task (images, audio, etc). These must be nested inside the inputs object.
inputs object.inputs»referenceImagesreferenceImages
array of stringsitems: 11 limitList of reference images (UUID, URL, Data URI, or Base64). Photo of the person to animate.
inputs»referenceVideosreferenceVideos
array of stringsitems: 12 limitsList of reference videos (UUID or URL). Footage of the character whose likeness and gestures the avatar takes. A video of a realistic person is rejected. For a realistic person, use
referenceImagesoravatar.
inputs»audioaudio
stringAudio input (UUID or URL). Speech the avatar performs. The video runs the length of the audio.
inputs»avataravatar
stringHeyGen avatar ID for a photo or video avatar.
Allowed values500 values
inputs»backgroundbackground
stringBackground image for the generated video (UUID, URL, Data URI, or Base64).
Core Parameters
Primary parameters that define the task output.
model
stringrequiredvalue: heygen:avatar@6Send
autoinstead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See Model Router.Learn more3 resources
positivePrompt
stringmin: 1max: 1200Text prompt describing elements to include in the generated output. Directs gestures, facial expression, posture and camera.
Learn more1 resource
- PromptsLEARN
- Prompts
width
integerpaired with heightWidth of the generated media in pixels.
Learn more2 resources
height
integerpaired with widthHeight of the generated media in pixels.
Learn more2 resources
resolution
stringdefault: 1080pResolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. With reference media,
1080pgives a short edge of about 1080 px with the long edge capped at 1920 px, and2kabout 1620 px with the long edge capped at 2880 px.Allowed values2 values
speech
objectrequired*Settings for speech generation.
Properties6 properties
speech»texttext
stringmin: 1max: 5000Text to convert to speech.
speech»voicevoice
stringVoice identifier to use for speech generation.
Allowed values2300 values
speech»languagelanguage
stringmin: 1Language code for speech generation.
Allowed values186 values
speech»volumevolume
floatmin: 0max: 1step: 0.1default: 1Volume level of the generated speech.
speech»speedspeed
floatmin: 0.5max: 1.5step: 0.01default: 1Playback speed of the generated speech.
speech»pitchpitch
floatmin: -50max: 50step: 0.1default: 0Pitch adjustment for the voice.
Settings
Technical parameters to fine-tune the inference process. These must be nested inside the settings object.
settings object.settings»backgroundColorbackgroundColor
stringHex color code for solid background (e.g. #ff0000).
settings»captioncaption
booleanEnable captions. When true, returns a sidecar SRT file and burns captions into the rendered video.
settings»fitfit
stringHow the avatar is scaled to the output canvas. When omitted, the server picks the best option based on source and canvas orientations.
Allowed values2 values
- Scales to fill the canvas, and may crop edges.
- Scales to fit entirely, and may show background.
settings»motionExpressivenessmotionExpressiveness
stringdefault: defaultAmount of gesture and facial motion.
positivePromptoverrides it where they overlap.Allowed values2 values
- The model's usual motion.
- Fewer and smaller gestures, and calmer facial expressions. Does not disable motion.
settings»removeBackgroundremoveBackground
booleanRemove the avatar background. Video avatars must be trained with matting enabled.