Skip to main content

heygen/video-1/text-to-video

HeyGen Video 1.0 is HeyGen’s scene-generation model; its text-to-video endpoint creates 5–15 second clips from a written brief at 480p or 768p with AAC stereo audio.

From $0.03/s

Workbench

Input

Text to video
308/32000
Describe who appears, what moves, where the shot takes place, and what should be heard. A specific action and camera view make the returned scene easier to evaluate. at least 1 characters · at most 32000 characters
Choose a frame shape from this endpoint’s current options before submitting. Plan the framing around the destination rather than relying on the scene text to select it.
affects price
Choose 480p or 768p for text generation.
Durationaffects price
Request between 5 and 15 seconds. Five-second files in our tests lasted 5.18–5.26 seconds after frame rounding, while billing counted five output seconds. no lower than 5 · no higher than 15
Prompt optimization
disabledturboquality
Set disabled when you want to avoid a prompt rewrite. Both turbo and quality let the model rewrite your brief, so hold this choice steady when comparing prompts.
Seed
Keep the seed fixed and change one scene detail to make a comparison easier. Matching the seed does not guarantee an identical result. no lower than 0 · no higher than 2147483647
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result

Missing the model you need?

HEYGEN VIDEO GENERATION

HeyGen Video 1.0 API at a glance

Turn a scene brief, a portrait, or a set of references into a short clip, with the endpoint chosen around what the shot needs to preserve.

Requested clip duration
5–15 s
Billing counts the requested output seconds; measured five-second files ran 5.18–5.26 seconds.
Native photo tier
2K
The image-to-video 2k test returned 2688×1536 pixels.
Combined reference items
12
Count images, videos, and audio clips together against the reference endpoint’s cap.
Text-video test fps
24 fps
A five-second 480p text run returned 832×480 with an AAC stereo audio track.

Results

What you can make with HeyGen Video 1.0

  • Text and audio

    A written scene becomes a clip

    Text-to-video creates a 5–15 second scene at 480p or 768p and includes an audio track. Our 480p, five-second run returned 832×480 at 24 fps with AAC stereo audio in about 10 seconds of processing. That observation describes one run, rather than a turnaround promise.

    Text-to-video at 480p for 5 seconds in 16:9, with the turbo prompt rewrite and generated studio sound.

  • Photo animation

    Keep the source person in view

    Image-to-video uses image_url and a movement prompt to animate a supplied photo. Our 480p, 1080p, and 2k tests kept the source person and composition, with the 2k run delivering 2688×1536 pixels. Choose this input pattern when continuity with a particular photograph matters.

    The 2k tier of the wine bar test at 2688×1536 pixels, keeping the composition of the source photo.

  • Reference roles

    Cast the person and the object separately

    Reference-to-video can combine images, videos, and audio clips within a 12-item total. The two-image portrait-and-bottle test produced a vertical shot with the man holding the supplied bottle. A separate mixed-reference run followed its video closely and lost the photo’s face, so assign a clear purpose to each input.

    Reference-to-video in 9:16 at 480p, where the man from the first image holds the bottle from the second image.

  • Controlled comparisons

    Change a prompt without losing the setup

    The seed and prompt_optimization_mode controls help organize revisions. Keep a seed fixed while comparing one change; it does not guarantee an identical result. Select disabled to avoid a prompt rewrite, or try turbo or quality when you want the model to rewrite the brief.

Before you run it

What to know before you run HeyGen Video 1.0

All modes
Request a duration from 5 to 15 seconds. Text-to-video and reference-to-video offer 480p or 768p; 1080p and 2k belong to image-to-video.
Reference to video
Keep the combined reference count at 12 or fewer and reference-video duration at 15 seconds or less. Use text, voices, and likenesses you have rights to use, and never impersonate a real person.
All modes
The 5.18–5.26 second measured files came from five-second requests rounded to whole frames. Save and review the result; that extra playback time does not increase the requested seconds billed.

Use cases

What to build with the HeyGen Video 1.0 API

  • A scene before the shoot

    Send a text brief for a potter in their thirties, wearing a canvas apron in a sunlit studio, turning toward a shelf. A five-second request at 480p gives you a concept clip with an audio track to review before a shoot.

  • A portrait with a small gesture

    Provide a licensed portrait of a woman in her thirties in an evening dress beside a window, then ask for a head turn and a slow camera move. Image-to-video returns a short animation guided by that photo; inspect the person and composition against the source.

  • A presenter with a supplied product

    Attach a man’s portrait as <Picture 1> and a dropper-bottle photo as <Picture 2>, then request a 9:16 shot of him holding the bottle. Our two-image test used both references and took about 158 seconds to process.

  • A motion-led concept

    Supply a portrait, a four-second motion clip, and an audio reference with roles named in the prompt. Our mixed-input run followed the video’s motion and scene closely, but did not retain the portrait’s face; use this pattern when motion matters more than that face.

  • A larger photo-based deliverable

    Pair a source photo with a restrained movement prompt and select 1080p or 2k for image-to-video. Our five-second tests returned native 1890×1080 and 2688×1536 outputs while keeping the source person.

Prompts

HeyGen Video 1.0 prompt examples you can copy

  • Text to video

    An evening arrival

    A woman in her mid thirties in a forest-green evening dress pauses under the canopy of a small theater after rain. Warm lobby light meets cool blue street light. She turns toward the doorway with a quiet smile as the camera makes a slow, level push toward her. Five-second continuous shot, restrained and expectant mood. Sound: distant tires on wet pavement and a door opening, no music.

    Why it works. A defined wardrobe, two light sources, and one turn give the scene a clear visual direction without competing actions.

    Try this prompt
  • Text to video

    Linen at the harbor

    A man in his late thirties wearing an open-collar linen shirt and a navy jacket stands beside a harbor railing at dusk. He looks from a folded map to the boats, thoughtful and relaxed. Static medium shot with soft amber reflections on his face and pale blue water behind him. Five seconds, natural movement. Sound: ropes tapping a mast and gentle water, no dialogue or music.

    Why it works. The gesture and fixed framing make the intended movement easy to assess; the sound direction identifies separate sources.

    Try this prompt
  • Text to video

    A quiet rooftop toast

    A couple in their thirties stand close together at a rooftop table, one wearing a burgundy evening dress and the other a charcoal suit with an open-collar shirt. Under warm string lights against a violet city sky, they raise their glasses toward each other, smiling. Static medium shot, intimate but understated mood, five seconds. Sound: a gentle glass clink and distant traffic, no music.

    Why it works. Specific clothing, a simple shared action, and a single camera setup keep the scene brief coherent.

    Try this prompt
  • Image to video

    A portrait catches the light

    Animate the supplied portrait of a woman in her thirties wearing a cream blouse in a bright studio. Keep the source person and composition as she gently turns her head toward the window and settles into a calm smile. The camera remains still, soft morning light across her face, five seconds. Sound: quiet indoor ambience, no music.

    Why it works. The instruction concentrates on what changes after the photo and states which visual elements should remain.

    Try this prompt
  • Image to video

    The tailor at the workbench

    From the supplied photograph of a man in his thirties wearing a waistcoat over a rolled-sleeve shirt in a tailoring workshop, animate a small glance from the workbench toward the camera. Retain the source person and composition, warm side light, calm and attentive mood. Five-second shot with a still camera. Sound: soft workshop room tone, no speech or music.

    Why it works. A restrained glance makes a useful photo-animation trial before selecting a larger native resolution tier.

    Try this prompt
  • Reference to video

    A portrait and a bottle

    The man in his thirties from <Picture 1>, wearing a pale blue shirt, stands in a softly lit bathroom and holds the dropper bottle from <Picture 2> beside his face. Keep the supplied person and bottle recognizable as he turns slightly toward the lens. Vertical 9:16 composition, static camera, warm morning light, composed mood, five seconds. Sound: quiet room ambience, no music.

    Why it works. The numbered tokens give the person and product separate roles; pair this prompt with two image references and use vertical 9:16 framing.

    Try this prompt

Pricing

HeyGen Video 1.0 API pricing

A 5-second clip starts at $0.15 at 480p and $0.72 at 2K.

Get started

How to use the HeyGen Video 1.0 API in three steps

  1. Step 1

    Match the endpoint to the input

    Choose text-to-video for a written scene, image-to-video for a photo, or reference-to-video for multiple source items. Photo animation offers 1080p and 2k when you need those tiers.

  2. Step 2

    Prepare a focused scene brief

    Describe the person, wardrobe, setting, lighting, and one visible action. For references, tie the action to tokens such as <Picture 1> and <Picture 2>, and use text, voices, and likenesses you have rights to use.

  3. Step 3

    Submit the generation task

    POST to https://api.spicyapi.ai/api/v1/jobs/createTask with Bearer authentication and JSON such as {"model":"heygen/video-1/text-to-video","input":{"prompt":"A potter in their thirties turns toward a shelf.","duration_seconds":5,"resolution":"480p"}}.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

HeyGen Video 1.0 API FAQ

About HeyGen Video 1.0

Build your next HeyGen Video 1.0 API request around the material you already have. A written scene belongs in text-to-video; a photo whose person and composition matter belongs in image-to-video, with native tiers through 2K. Use reference-to-video to combine a presenter and a product, and name their roles with <Picture 1> and <Picture 2>. Our mixed-reference test showed why a motion clip needs care: it guided the scene but displaced the photo's face. Check the displayed rate, request 5–15 seconds, then review the returned clip before planning another shot.

Related models and next tasks