HeyGen Video 1 is HeyGen's first general-purpose video model. The video and its soundtrack come out of the same pass, so a character's lines, room tone, and on-screen sounds line up with the picture without a separate audio step.

Why creators choose HeyGen Video 1

Dialogue and sound in the same pass

HeyGen Video 1 writes the audio together with the frames. Put spoken lines in your brief and the character says them, with ambience and sound effects to match the scene. The clip is ready to play the moment it finishes.

Low cost per second

HeyGen Video 1 is one of the most affordable video models on Craze, which makes it a good fit for drafts, storyboards, and high-volume social clips where you want sound without paying premium rates.

Start from text or a first frame

Describe the shot in words, or give Craze an image to use as the opening frame. The model animates from that frame, keeping the subject and setting you chose.

Six aspect ratios

The model supports 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, so one brief can cover widescreen, square, and vertical placements.

How to use HeyGen Video 1 in Craze

1. Start a project and describe the video you want to make. Add an image if you want it as the opening frame.
2. Say you want HeyGen Video 1, or pick it in the Models panel. If you don't name a model, Craze shows compatible options with prices before it plans.
3. Craze plans your clips, writes the prompt for each one, and generates the video with sound.
4. Review the clip in the editor. Regenerate any shot that misses, keep what works, and keep editing.

If a line of dialogue matters, put it in quotes in your brief: "She looks up and says 'We made it'" is more useful than "she reacts."

HeyGen Video 1 pricing

You pay per second of video. 480p is the most affordable tier and 768p costs more. Longer clips cost proportionally more. $0.023 per second of video.

Use the cost calculator on this page to estimate the price of any clip before you generate.

Who HeyGen Video 1 is for

Talking scenes and short skits

Clips where a character speaks to camera or two people trade lines benefit most from audio generated with the picture.

Social drafts and volume work

At its per-second rate, HeyGen Video 1 suits quick iterations, test concepts, and batches of vertical clips.

HeyGen Video 1 vs other models

If you need 1080p or clips longer than 15 seconds, Wan 3.0 runs up to 30 seconds at 1080p with optional sound. For reference-driven continuity across shots, Seedance 2.5 accepts reference images and videos.