Create a new avatar training job from an image URL.
Supported image formats: jpg, jpeg, png, bmp, webp.
Video upload is not allowed - only image URLs are accepted.
Returns a jobId (for polling status) and an avatarId (for referencing the avatar in sessions).
The license key can be passed as either a query parameter or a request header.
NavTalk API license key (e.g. sk_navtalk_...)
Display name for the avatar. Must be unique per account.
"my-video-avatar"
URL of the source image file. Supported image formats: jpg, jpeg, png, bmp, webp. Video upload is not allowed.
"https://example.com/photo.jpg"
The provider ID to use (obtained from /provider/list).
"b92a28fb2ea737457c7f13ba554759c0"
The model key to use (obtained from /model/list). For ElevenLabs agents, see ElevenLabs Agents Quickstart.
"agent_3201khcbet2vf349gpmtfg83q0hy"
The voice key to use (obtained from /voice/list).
"CwhRBWXzGAHq8TQ4Fs17"
Optional opening message the avatar says at the start of a conversation.
"Hi! How can I help you today?"
Optional system prompt that controls the avatar's behavior and personality.
"You are a helpful assistant."