logo
RunComfy
  • ComfyUI
  • TrainerNew
  • Models
  • API
  • Pricing
discord logo
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

HeyGen Video: Text-to-Video Scenes with Sound on Models and API | RunComfy

heygen/heygen-video/text-to-video

HeyGen Video turns a prompt into a short clip whose picture and sound are generated together.

Subject, place, camera, dialogue, and sound for one shot.
Clip length in whole seconds.
Frame size. 1080p and 2k only support 16:9 and 9:16.
Frame shape. 1080p and 2k only support 16:9 and 9:16.
How far the prompt is expanded before the shot. Disabled keeps your text as written.
Optional repeat handle. Leave empty to let the service choose.
Idle
The rate is $0.009 per second at 480p and 768p, and $0.028 per second at 1080p and 2k.

Introduction To HeyGen Video

HeyGen's HeyGen Video Text To Video builds a 5 to 15 second scene, with its own sound, from $0.009 per second.
Trading a separate shoot and a later voice pass for one scene call suits editors, trainers, and product teams.
For developers, HeyGen Video on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Product Beats | Training Inserts | Dialogue Coverage.

Why Choose This Page#


A mood word often returns a generic room. This page builds the subject, the light, and the sound in one clip, so dialogue and room tone share the same description.


AdvantageWhat you get
Picture and soundHeyGen Video writes the track with the frames.
A length you setAny whole second from 5 to 15.
Four sizes480p, 768p, 1080p, and 2k.
A repeatable shotA HeyGen Video seed lets the next run stay close.

This page is text to video only. You do not upload a first frame here. The prompt is the whole brief.


On RunComfy, try a shot in the model UI, then send the same prompt and settings through the HTTP API.


Best Use Cases#


  • Product beats: HeyGen Video can hold one object and one action.
  • Training inserts: One spoken step, with the hands mostly still.
  • Place shots: A HeyGen Video street or kitchen, with the sound of that room.
  • Dialogue coverage: One speaker, one line, a locked camera.
  • Style tests: Name a real lens for HeyGen Video instead of asking for a cinematic look.

How It Works#


  1. Open the text-to-video template.
  2. Write a HeyGen Video prompt that names the person, the place, the camera, and the sound.
  3. Set duration from 5 to 15 seconds. Spoken HeyGen Video lines fit at about two or three words a second.
  4. Choose resolution. 768p is the default. 1080p and 2k cost more and only accept 16:9 or 9:16.
  5. Choose a HeyGen Video aspect ratio that the resolution allows.
  6. Leave enhancement on quality, or switch it off when the prompt is already complete.
  7. Set a HeyGen Video seed if you will change one sentence and run again.
  8. Play picture and sound together. For production, send prompt, duration, resolution, aspect_ratio, prompt_enhancement, and optional seed.

Parameters#


These are the controls on this page.


ParameterRequiredTypeDefaultRange / OptionsDescription
prompt*Yes (*)StringLisbon street line1–32000 charactersSubject, place, camera, dialogue, and sound.
durationNoInteger55–15Length in whole seconds.
resolutionNoString768p480p, 768p, 1080p, 2kFrame size.
aspect_ratioNoString16:921:9, 16:9, 4:3, 1:1, 3:4, 9:16HeyGen Video frame shape.
prompt_enhancementNoStringqualityturbo, quality, ultraquality, disabledExpansion before the shot. Disabled keeps your text.
seedNoIntegerEmpty0–4294967295Optional repeat handle.

Pricing#


HeyGen Video bills each second of the duration you set. 1080p and 2k share one rate.


ResolutionPer second5 seconds10 seconds
480p$0.009$0.045$0.09
768p$0.009$0.045$0.09
1080p or 2k$0.028$0.14$0.28

Aspect ratio does not add a HeyGen Video fee. The charge is the same per second for 9:16 and 16:9 at one resolution.


Prompting & Reference Tips#


  • Name the camera: For HeyGen Video, a 50mm on a tripod beats the word cinematic.
  • Say the sound: Name room tone, and say no music when you do not want a score.
  • One action: A person speaking is safer in HeyGen Video than hands building a device.
  • No stray marks: Ask for no logos and no printed words.
  • Hold the seed and change one HeyGen Video clause at a time.
  • Turn enhancement off when the prompt is already a full shot list.

Related Models

kling-video-o1/standard/image-to-video

Create 1080p cinematic clips from stills with physics-true motion and consistent subjects.

kling-video-o3/4K/reference-to-video

Cinematic 4K reference-to-video at $0.419 per second of output.

minimax-h3-fast/reference-to-video

MiniMax H3 Fast: video from one clip and up to four images

heygen-voice/text-to-audio

Read plain text aloud in a public voice and return one WAV file.

wan-2-2/animate/video-to-video

Transforms input clips into synced animated characters with precise motion replication.

flux-3-max/text-to-video

FLUX 3 Max Text To Video turns a prompt into a short clip.

Frequently Asked Questions

What is HeyGen Video used for in a text-to-video workflow?

HeyGen Video builds a 5 to 15 second scene from a written prompt, with picture and sound in the same clip. This page is text to video only. It fits product beats, training inserts, and one line of dialogue.

Which lengths, sizes, and shapes can HeyGen Video render?

HeyGen Video accepts any whole second from 5 to 15. Resolutions are 480p, 768p, 1080p, and 2k. Aspect ratios include 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, but 1080p and 2k only accept 16:9 or 9:16.

How should I write a HeyGen Video prompt?

Name the person, the place, the lens, and the sound in the HeyGen Video prompt. A 50mm on a tripod is clearer than the word cinematic. Say that you want no music, no logos, and no printed words when those should stay out of frame.

What does prompt enhancement change in HeyGen Video?

HeyGen Video can expand the prompt with turbo, quality, or ultraquality, and quality is the default. Choose disabled when the prompt is already a full shot list. A seed lets the next run stay close while you change one sentence.

What input limits should I know before using HeyGen Video?

HeyGen Video prompts can be up to 32000 characters. Duration must be a whole number from 5 to 15. You do not upload a first frame on this page. One person speaking is safer than hands building a small object.

Can I try HeyGen Video in the Playground Web UI and then call the same model from the API?

Yes. Try a HeyGen Video shot in the Playground Web UI, then send the same prompt, duration, resolution, aspect ratio, enhancement, and optional seed through the RunComfy API. The API uses the same model. It does not promise a fixed turnaround or unlimited concurrency.

How much does it cost to generate with HeyGen Video on RunComfy?

HeyGen Video bills each second of the duration you set: $0.009 at 480p, $0.009 at 768p, and $0.028 at 1080p and 2k. A 5-second 768p clip is $0.045. Aspect ratio does not add a fee. Generations consume usd credits.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Kling 4.0 Image to Video
  • Kling 4.0 Reference to Video
  • Kling 4.0 Video Editing
  • Wan 3.0
  • Wan 2.5
  • MiniMax H3 Fast
  • View All Models →
Image Models
  • Seedream 4.5
  • Seedream 5.0 Pro
  • Flux 2 Pro
  • Qwen Image Edit 2511 LoRA
  • seedream 4.0
  • Nano Banana Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Examples Of HeyGen Video

Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...