**HeyGen Video is our general-purpose video model, built on MiniMax H3 and post-trained by HeyGen.** Give it a prompt and it generates the whole scene: subject, setting, light and sound together, in one call. Each clip runs 5 to 15 seconds with its own audio track of dialogue, ambience and sound effects, so there is no separate speech pass, lip-sync step or avatar to pick.
One model, `heygen-video-1`, called in three ways:
| Mode | You give it | You get |
| - | - | - |
| **Text to video** (`text_to_video`) | A prompt | A new scene with its sound |
| **Image to video** (`image_to_video`) | A prompt and one image | A clip that opens on your image as its first frame |
| **Reference to video** (`reference_to_video`) | A prompt and your images, videos or audio | A new scene that keeps the products, people or places you supplied |
It is a different tool from the [avatar rendering engines](/models). Those animate a look you already own from a script you already wrote. This one invents the subject, the setting, the light and the sound at once, from a description. The rest of this page starts with the call itself, then what the model is good at and how to prompt it, then the full API reference.
export const HERO = [{
"src": "https://resource2.heygen.ai/videos/66c20e44a62c40a58cf8c51210dab761/66c20e44a62c40a58cf8c51210dab761/01a0f043-0a69-7f00-9129-2c3226ffd9f4.mp4",
"poster": "/images/heygen-video/L10_train_c.jpg",
"label": "The audio comes from the same prompt",
"teaches": "Near silence first, then each sound of the arrival, in order",
"prompt": "An empty suburban railway platform at dawn, completely still, wet concrete and a yellow safety line, overhead wires, a pole-mounted platform display that reads REALISTIC SOUND in amber LED capitals. Static camera on a tripod at platform height, Shot on an ARRI Alexa Mini, 35mm at f/4, fine film grain, 24 fps, muted true-to-life colour, no teal-orange grade, no CG sheen. Soft overcast daylight. For the first three seconds nothing moves and it is almost silent: faint wind, one distant bird. Then a modern commuter train with a plain unmarked body sweeps in from the left and fills the frame. Audio: a horn blast, wheels hammering the rail joints, a rush of air, brakes squealing as it slows. No people. No logos, brand names, printed words or badges anywhere in frame except the display. No music."
}, {
"src": "https://resource2.heygen.ai/videos/66c20e44a62c40a58cf8c51210dab761/66c20e44a62c40a58cf8c51210dab761/01a0f07c-1ef6-7718-b775-2eaaf39f3252.mp4",
"poster": "/images/heygen-video/L16_cello_b.jpg",
"label": "Naming the lens does the work",
"teaches": "A body, a focal length and a stop set the look",
"prompt": "A cellist in a rehearsal room draws one long bow stroke, seen from the side at medium distance, face turned away. Shot on an ARRI Alexa Mini LF, 50mm T2, locked off on a tripod. Warm lamp light and a window. Fine film grain, true-to-life muted colour, no teal-orange grade, no retouching, no beauty filter, no glamour lighting, real textures and materials. One clear subject, simple uncluttered frame, natural physical motion. Faces small or turned away. No logos, brand names, printed words or badges anywhere in frame. No music."
}, {
"src": "https://resource2.heygen.ai/videos/66c20e44a62c40a58cf8c51210dab761/66c20e44a62c40a58cf8c51210dab761/01a0f07b-7dba-74e5-a0f0-62a03a4edd7b.mp4",
"poster": "/images/heygen-video/L16_potter_a.jpg",
"label": "Asking for texture, then forbidding the fix",
"teaches": "Real materials in; retouching and glamour light ruled out",
"prompt": "Wide shot of a potter at a spinning wheel in a quiet studio, a clay vessel rising between the potter's hands as the wheel turns. Shot on an ARRI Alexa Mini LF, 35mm T2.8, locked off on a tripod. Soft window daylight. Fine film grain, true-to-life muted colour, no teal-orange grade, no retouching, no beauty filter, no glamour lighting, real textures and materials. One clear subject, simple uncluttered frame, natural physical motion. Faces small or turned away. No logos, brand names, printed words or badges anywhere in frame. No music."
}, {
"src": "https://resource2.heygen.ai/videos/66c20e44a62c40a58cf8c51210dab761/66c20e44a62c40a58cf8c51210dab761/01a0f043-b312-7ac6-bb47-254fd2364f99.mp4",
"poster": "/images/heygen-video/L10_dish_a.jpg",
"label": "Stillness reads as production value",
"teaches": "A static camera, one slow push, nothing handled",
"prompt": "A plated restaurant dish on a matte ceramic plate on a dark wooden table, steam rising gently from it, warm low restaurant light, the room softly blurred behind. Shot on an ARRI Alexa Mini, 85mm at f/2, fine film grain, 24 fps, muted true-to-life colour, no teal-orange grade, no CG sheen. Static camera, slow very slight push in. No people in focus, no hands handling anything. No logos, brand names, labels, printed words, numbers or signage anywhere in frame. No music."
}, {
"src": "https://resource2.heygen.ai/videos/66c20e44a62c40a58cf8c51210dab761/66c20e44a62c40a58cf8c51210dab761/01a0f028-1eff-7bc1-bf91-e344678a8ffd.mp4",
"poster": "/images/heygen-video/L_ttq_d.jpg",
"label": "Short lettering, spelled out",
"teaches": "Three capitalised words, spelled exactly, and nothing else legible",
"prompt": "subject_definitions:\n