Skip to main content

Introducing HeyGen Video — Generate Cinematic Clips from a Prompt

HeyGen Video is our first general-purpose video model. Generate cinematic clips from a text prompt, image, or reference video via API — at a fraction of competitor prices.

Written by Avi

Big news — HeyGen just launched its first-ever general-purpose video model. ✨

Up until now, HeyGen has been home to our avatar and voice models. Today, we're adding something entirely new: HeyGen Video, a model that generates cinematic, production-quality clips from a text prompt — no avatar required. Think of it like Seedance 2.0, but faster, more affordable, and built in-house.

Three Modes, One Model

Text to Video (T2V) — Describe a scene in a prompt and get back a cinematic clip, complete with synchronized audio (dialogue, ambience, and sound effects) generated in the same call. No footage required.

Image to Video (I2V) — Drop in a reference image and the model animates it into a clip. Great for product shots, real estate, lifestyle content, and more.

Reference to Video (Ref2V) — Provide a reference video to guide the motion, composition, or style of your output. Billing covers input + output seconds; image and audio references are always free.

How Does It Compare?

In blind side-by-side evaluations against the leading models on the market — Seedance 2.5, Seedance 2.0, H3 Max, and Kling 3.0 — HeyGen Video ranked #1 in quality. And it costs a fraction of what competitors charge:

Model

List price per second (768p)

HeyGen Video

$0.03

H3 Max Turbo

$0.04

H3 Max

$0.08

Kling 3.0 Pro

$0.168

Seedance 2.0

$0.303

Veo 3.1

$0.40

Eval conducted with 4,800 blind votes on the Artificial Analysis Arena query set.

Pricing

HeyGen Video is billed per second of output video. We're running a 50% launch promotion through the end of October — prices below include the discounted rate:

Mode

Resolution

Promo rate (now)

Standard rate (Nov+)

Text to Video

480p

$0.01 / sec

$0.02 / sec

Text to Video

768p

$0.015 / sec

$0.03 / sec

Image to Video

480p

$0.01 / sec

$0.02 / sec

Image to Video

768p

$0.015 / sec

$0.03 / sec

Reference to Video

480p

$0.02 / sec

$0.04 / sec

Reference to Video

768p

$0.03 / sec

$0.06 / sec

💡 Ref2V note: billing covers input video seconds + output video seconds. Image and audio references don't add to your cost.

Where to Access It

HeyGen Video is available via API right now. Web platform access is coming soon.

You can access it through:

👋 Ready to get started? Grab your API key at app.heygen.com/developers/api and explore the full API documentation.

Last Updated: September 30, 2026

Did this answer your question?