HeyGen Video
HeyGen Video is a general text-to-video and image-to-video model on fal, built on MiniMax H3 and post-trained by HeyGen. It is not HeyGen's avatar product: there is no presenter, script or voice to pick, just a prompt that becomes a 5 to 15 second clip with its own sound. It renders at 480p, 768p, 1080p or 2K in six aspect ratios, and fal's endpoint rewrites the prompt by default with a prompt_enhancement setting (turbo, quality, ultraquality or disabled).
Anvisha Pai, Co-founder & CEO, Voyager
HeyGen / MiniMax
›What we asked for
A self-portrait of HeyGen Video, the video model with native sound: a jazz trio playing in a smoky club, close on the drummer's brushes then the double bass, warm light, the music itself audible and in time.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
At a glance
- Price
- $0.02 a second at 480p and 768p on fal, $0.06 at 1080p and 2K, read October 22, 2026. A five-second 768p clip is $0.10.
- Measured wait
- 21 to 41 seconds from queue submission to a five-second 768p clip, across nine prompts in one batch. Not a service guarantee.
- Length
- 5 to 15 seconds, in whole seconds.
- Audio
- Every clip comes with its own sound; there is no setting to turn it off.
- Prompt rewriting
- On by default (turbo). quality and ultraquality rewrite more; disabled sends your prompt as written.
Other Hailuo models: H3 Max Turbo, H3 Max, MiniMax H3, Hailuo 2.3. Compare all 5.
Anvisha's take
HeyGen Video is the cheapest model on our roster and it does not look it. Nine five-second clips at 768p cost $0.90, and each came back in 21 to 41 seconds. The title card spells both lines, the market is dense from above with the busker and the bunting (and two golden dogs, one on a lead), the pour keeps a steady stream into a ribbed dripper with the grounds blooming, and the image-to-video clip keeps our photographed dripper exactly. Like the H3 it is built on, it edits when it wants to: the self-portrait cut from the drummer's brushes to the double bass just as H3's did, and the spill cut away from the glass to a macro of three ice cubes, so the spill itself is never shown. The turntable dripper became a faceted bowl with a spout. We left prompt enhancement at fal's default, turbo. For cheap drafts with sound I would start here. These are frame-based observations; audio was present on every clip but not scored by ear.
HeyGen Video real output: the same 9 clips every model gets
Every video model on this site gets the same 9 clips, so you can compare like with like. These are the clips HeyGen Video returned, one try each, nothing re-rolled or retouched. Each tile shows one frame of the clip until you press play. Generated on . The 9 clips took 21 to 41 seconds each and cost $0.90 in total.
A clean product shot that holds its shape through a full slow rotation.
›What we asked for
A matte black ceramic pour-over coffee dripper rotating slowly on a white turntable, soft studio light, seamless white background, product video, no text.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
A face, lip sync and a spoken line, where the model makes audio.
›What we asked for
A woman in her 40s with short grey hair stands in a bright kitchen, looks at the camera and says 'Good morning, the coffee is ready', natural window light, handheld feel, she smiles at the end.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
Set text that stays spelled correctly while it moves.
›What we asked for
A title card reading 'MODA SUMMER SESSIONS' animates in over slow-motion footage of a festival crowd at dusk, then a smaller line 'Friday 12 June' fades in beneath it. Bold condensed type, tangerine on navy.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
A steady drone push-in with stable geometry.
›What we asked for
Drone shot pushing slowly forward over a coastal town at sunrise, terracotta roofs, fishing boats in the harbour, long shadows, cinematic and steady.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
A spill in slow motion: does water behave like water.
›What we asked for
A glass of water tips over on a wooden table and spills in slow motion, water and three ice cubes sliding across the wood, macro lens, morning light.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
Hands, a kettle and a steady pour without extra fingers or teleporting objects.
›What we asked for
Close-up of hands pouring hot water from a gooseneck kettle in slow circles into a pour-over coffee dripper, steam rising, shallow depth of field, warm cafe light.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
Many people and objects moving at once without merging.
›What we asked for
A crowded Saturday farmers market seen from slightly above, shoppers with tote bags, a dog on a leash, a busker with a guitar, bunting swaying, late morning light, gentle camera drift.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
A named style held across every frame rather than drifting to photoreal.
›What we asked for
A lighthouse on a rocky cliff in a storm, in the style of a Japanese ukiyo-e woodblock print, waves crashing in flat colour with visible wood grain, animated like moving paper cutouts.
heygen/heygen-video/text-to-video
aspect_ratio: 16:9, resolution: 768p, duration: 5
returned 1344 by 768 pixels
Bring a still product photo to life without changing the product.
›What we asked for
The coffee dripper slowly fills as coffee drips through it, steam rising, the camera drifting gently around it, the dripper itself unchanged. (starting from The Nano Banana Pro product shot from the image fixture set.)
heygen/heygen-video/image-to-video
resolution: 768p, duration: 5
returned 768 by 768 pixels
How the cost under each picture was worked out: fal's HeyGen Video rate of $0.02 per second at 768p (fal.ai/models/heygen/heygen-video/text-to-video and fal's pricing API, read 2026-10-22) for the 5 seconds requested; fal does not return the charge.
Compare HeyGen Video
HeyGen Video pricing
| Where | Unit | Price | Source |
|---|---|---|---|
| fal | Second at 768p The same rate at 480p, on text-to-video and image-to-video. fal's pricing API agrees. | $0.02 | fal model page, read |
| fal | Second at 1080p or 2K | $0.06 | fal model page, read |
Is HeyGen Video free?
The fal endpoints are paid per second of video. We have not found a free allowance for this model.
- •HeyGen's own avatar app has its own plans; they are a different product from this model.
fal model page, read
Where to use HeyGen Video
- fal, text-to-video · Hosted API and playground; the endpoint used for eight of the clips below.
- fal, image-to-video · The image becomes the first frame; used for the image-to-video clip.
- Voyager · Runs inside Voyager, the agent for creative work, with your own fal key.
Voyager
Run HeyGen Video inside Voyager
Voyager is an agent for creative work that runs every model in this reference, HeyGen Video included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.
What we noticed running HeyGen Video
- •The glass starts to tip, then the clip cuts to a macro of exactly three ice cubes in a small puddle. The spill itself is never on screen. See the physics clip.
- •The dripper became a faceted black bowl with a pouring spout and no foot. See the product turntable clip.
- •Kept the photographed dripper exactly with a still camera; the coffee level rises inside it like a cup. See the image to video clip.
- •Both lines spelled correctly in tangerine over a concert crowd; the type sits straight on the dusk sky rather than on navy. See the animated title card clip.
- •Self-portrait: cut from the drummer's brushes to the double bass inside five seconds, as MiniMax H3's own self-portrait did on the same prompt.
HeyGen Video limits and API parameters
| Limit | Value |
|---|---|
| Duration | 5 to 15 seconds, in whole seconds; 480p, 768p, 1080p or 2K. fal API schema, read |
| Output size | Our 16:9 clips came back at 1344 by 768, 24 frames a second, 5.26 seconds long, the same wider frame MiniMax H3 returns; the square product photo gave a 768 by 768 clip. fal API schema, read |
›Every setting, for developers
fal (heygen/heygen-video/text-to-video)
fal API schema, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| prompt | string | Up to 32,000 characters Required. | |
| duration | integer | 5 to 15 | 5 |
| resolution | enum | 480p, 768p, 1080p, 2k | 768p |
| aspect_ratio | enum | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | 16:9 |
| prompt_enhancement | enum | turbo, quality, ultraquality, disabled Left at the default for our clips. | turbo |
| seed | integer | Any Random when not set. |
HeyGen Video image-to-video
fal API schema, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| image_url | URL | Image Required; the first frame. No aspect ratio setting, the clip follows the image. |
What HeyGen Video will not make
The endpoints run a safety checker that only authorized callers can relax. None of our nine prompts was refused. Review the provider terms for your intended use.
fal API schema, read
Alternatives to HeyGen Video
Frequently asked questions
Is HeyGen Video an avatar model?
No. It is a general video model built on MiniMax H3 and post-trained by HeyGen: you describe a scene and get a clip with sound. HeyGen's talking-avatar products are separate.
How much does HeyGen Video cost?
On fal, $0.02 a second at 480p and 768p and $0.06 at 1080p and 2K, read October 22, 2026. A five-second 768p clip is $0.10; our nine cost $0.90.
How is HeyGen Video different from H3 Max?
Both are post-trained versions of MiniMax H3 on fal: HeyGen Video by HeyGen, H3 Max by fal. At 768p HeyGen Video lists $0.02 a second against H3 Max Turbo's $0.04 and H3 Max's $0.08. The H3 Max vs HeyGen Video page puts the two side by side.
How this page is made
Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.
