About HeyGen Avatar 6 Turbo: Reference to Video
HeyGen Avatar 6 Turbo, the faster, lower-cost tier of Avatar 6, makes an animated or illustrated character talk: it learns the character's look and motion from a reference video, then generates a new video of that character lip-synced to a speech track, with expression and gestures that follow what is being said.
Give it a clip of a cartoon, 3D, or illustrated character and recorded speech, plus an optional reference image of the same character to hold its design. The video keeps the reference clip's framing and aspect ratio and runs as long as the audio. An optional motion prompt directs gestures, expression, and posture in plain language.
Output is 1080p or 2K at 25 fps, billed per second of output, with 2K at a higher rate. It suits mascots, animated hosts, game and story characters, and dubbing a character into new lines. Use it for drafts, iteration, and high-volume work; Avatar 6 takes the same inputs at higher fidelity.
See what this model can do
A handful of real prompts and their outputs.
Ready to build with HeyGen Avatar 6 Turbo: Reference to Video?
Try HeyGen Avatar 6 Turbo: Reference to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "heygen-avatar-6-turbo-reference-to-video",
"input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/videos/waterfall.mp4",
"input_audio": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/audios/example.mp3",
"resolution": "1080p"
}'Request parameters
Every field HeyGen Avatar 6 Turbo: Reference to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_video | stringuri | Yes | — | Clip of the animated or illustrated character to bring to life. |
input_images | array<string> | No | — | Optional image of the same character. |
input_audio | stringuri | Yes | — | Speech the character performs. It sets the video's length. |
motion_prompt | string | No | — | Optional direction for gestures, expression, and posture. |
resolution | string | No | "1080p" | 1080p2k |