HeyGen Video: Cheapest AI Video API for Fast Video Generation

Production-quality video without production-level costs

From $0.01/s50% off through October

Opens developer settings. Sign in or sign up to create your key.

heygen-video-1text_to_video · 5 s · 768p · 16:9
Close-up of a race driver in a white helmet with a cyan and pink band, live action style
subject_definitions:
<Subject 1> is the real live-action cinematography of real people, real cars and real places.<Subject 2> is the scene rendered in it: a close-up of a driver in a plain white helmet with a cyan and pink band in the cockpit of a real unbranded Formula One car in one clean matte deep ink-navy paint with a single thin bright-cyan stripe, bare carbon fibre and plain black tyres, with no decals, numbers or markings anywhere, visor open, a young invented driver's focused eyes and sweat on the brow, the helmet shaking in the wind, the pale grey track blurring behind.
overall_soundscape:
Wind buffeting and an engine at full revs.

Shortened · 2,423 characters ·

Create AI videos from a prompt, an image, or your own references, with dialogue, ambience, and effects generated in the same API call. Production-quality clips start at $0.01 per second, built for the video your business needs every week.

See what HeyGen Video can create

Explore property walkthroughs, product shots, industrial scenes, small business moments, and craft, each generated from a single prompt with its own sound.

Text, image, and reference to video in one API

Start from a prompt, a first frame, or your own references. Every mode returns picture and sound together.

mode: text_to_video

Create videos from text

Describe the subject, setting, camera, and sound you want. HeyGen Video follows your brief literally rather than improvising, so the scene you described is the scene you get, with dialogue, ambience, and effects to match.

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.

Audio: a horn blast, wheels hammering the rail joints, a rush of air, brakes squealing as it slows.

Output · with sound
Empty railway platform at dawn with an amber display reading REALISTIC SOUND

mode: image_to_video

Turn images into videos

Upload a photo, product shot, or brand asset and HeyGen Video uses it as the literal first frame. The clip opens exactly as your image looks, then brings it to life with motion and sound.

Your imageWatercolour drawing of a navy race car on a pink and mint wash
Output · opens on your image
The same watercolour race car drawing, the first frame of the clip

mode: reference_to_video

Bring your own references

Supply up to 12 images, videos, and audio clips, and HeyGen Video builds a new scene that keeps the products, people, or places you gave it. The color, form, and markings of your product carry into the shot. The model reads the first 5 seconds of each reference video, so trim clips before you upload them.

Up to 12 references in total
  • max9 images
  • max3 videos
  • max3 audio
Output · with sound
A living room rendered as an animated mid-century screen print

Top-tier quality at a fraction of the price per second

In blind side-by-side tests, HeyGen Video performs alongside the top video models at a fraction of the price per second. At $0.01 per second through October (50% off the standard $0.02), it's practical for everyday business work: product demos, training, onboarding, and property walkthroughs. It's fast too: 3.7 seconds of diffusion time for a 10-second image-to-video clip.

$0.01/s
at 480p through October, then $0.02/s
3.7 s
diffusion time for a 10‑second image‑to‑video clip

What a clip costs

Mode
Resolution

$0.10 for a 10 s clip

$0.01/s at 480p · launch price through October

Standard: $0.20

1080p and 2k bill at 3x the 768p rate.

How to use HeyGen Video

Go from a prompt to a finished video with sound in three steps.

  1. 1 Start with a prompt, image, or reference

    Create an API key in your HeyGen developer settings, then describe the scene, subject, camera, and sound you want, or upload an image or references to guide the look of your video.

  2. 2 Direct your video

    Set the duration from 5 to 15 seconds, the resolution (480p, 768p, 1080p or 2k) and the aspect ratio (21:9, 16:9, 4:3, 1:1, 3:4 or 9:16). Name the lens, describe the sound and spell out any on-screen words exactly.

    • 21:9
    • 16:9
    • 4:3
    • 1:1
    • 3:4
    • 9:16
  3. 3 Generate, review and refine

    Generate your clip poll for the result or receive it by webhook and review it with its audio. Set a seed, then hold it and change one detail at a time until the shot is right.

Request
curl -X POST https://api.heygen.com/v3/models/videos \  -H "x-api-key: $HEYGEN_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "heygen-video-1",    "mode": "text_to_video",    "prompt": "A white ceramic cup of coffee steaming…",    "duration": 10,    "resolution": "768p",    "aspect_ratio": "16:9",    "seed": 42,    "callback_url": "https://example.com/hooks/heygen"  }'
# poll, or wait for the webhookcurl https://api.heygen.com/v3/models/videos/VIDEO_ID \  -H "x-api-key: $HEYGEN_API_KEY"{ "status": "completed", "seed": 42,  "video_url": "https://resource2.heygen.ai/…/VIDEO.mp4" }

HeyGen Video vs other AI video models

Compare the price, sound, and input modes that make HeyGen Video practical for everyday business video.

CapabilityHeyGen VideoOther AI video models
Price per secondFrom $0.01 (launch), $0.02 standardVaries by model
Native audioDialogue, ambience and effects in the same callVaries by model
Video length5 to 15 secondsVaries by model
Text to videoYesVaries by model
Image to videoYes, your image becomes the first frameVaries by model
Reference to videoUp to 12 images, videos and audio clipsVaries by model
Where to use itHeyGen API, OpenRouter, Runware and ComfyUIVaries by platform

Frequently asked questions (FAQs)

What is HeyGen Video?

HeyGen Video is HeyGen's first general-purpose video model, built for businesses that need production-quality video without production-level costs. Built on MiniMax H3 and post-trained by HeyGen, it generates a whole scene from a prompt: subject, setting, light, and sound together, in one call. Developers call it through the HeyGen API as heygen-video-1.

Where can I use HeyGen Video?

HeyGen Video is live now on the HeyGen API and through OpenRouter, Runware, and ComfyUI.

How much does HeyGen Video cost?

Pricing starts at $0.01 per second through October, 50% off the standard $0.02 per second, for 480p text-to-video and image-to-video. 768p, the API default, is $0.015 per second through October ($0.03 standard), and reference-to-video bills at a higher rate. 2k resolution bills at 3x the 768p rate.

Does HeyGen Video support text-to-video, image-to-video, and reference-to-video?

Yes. One model covers all three. Start from a written prompt, use an image as the first frame, or supply your own reference images, videos, and audio to keep a product, person, or place consistent in the shot.

How long are videos generated with HeyGen Video?

HeyGen Video generates clips from 5 to 15 seconds long, at 480p, 768p, or 2k, making it suitable for product demos, training, onboarding, property walkthroughs, and other short-form business video.

How is HeyGen Video different from HeyGen avatars?

HeyGen's avatar engines animate a look you already own from a script you already wrote. HeyGen Video invents the subject, setting, light, and sound from a description.

Why use HeyGen Video?

Every clip comes back with sound. There's no separate speech pass, lip-sync step, or audio edit. Pricing starts at $0.01 per second, making it practical to generate, review, and refine the video your business needs every week.

Is there a free tier for the HeyGen Video API?

HeyGen Video runs on paid API keys with pay-as-you-go pricing. At $0.01 per second, a 10-second 480p clip costs $0.10 through October.

What is HeyGen Video best at?

Short, contained shots: one subject, one place, one action, and a locked or barely moving camera. It is less reliable on long on-screen text, soft organic motion such as hair or petals, and close hand work, so keep lettering short and let speech carry any step-by-step instructions.

HeyGen Video is live now on the HeyGen API and through OpenRouter, Runware, and ComfyUI.