HeyGen's first general video model, with sound in every clip
HeyGen Video 1.0 AI Video Generator: Clips That Talk
Write the line in quotes and HeyGen Video 1.0 films the scene and speaks it, with the room sound and effects mixed in.
HeyGen Video 1.0 is the HeyGen video model built for scenes with sound. Every clip comes with spoken dialogue, ambience and effects, from 5 to 30 seconds, at 480p, 768p, 1080p or 2K, in six shapes from 21:9 cinemascope to 9:16 vertical. Start from a text prompt or bring one picture to life. On Pixel Dojo it sits beside every top video model in one plan, with six studios and Sensei, the AI director. We made every clip on this page here, and each one comes with its exact prompt so you can start from ours.
6.25 credits ($0.39) per 5 s clip at 768p. Included in every plan, from $10/month.
Already a member? Sign in
By Brian Lovett · Updated
Made with HeyGen Video 1.0: six scenes, all with sound
We made these six clips on Pixel Dojo: a 12 s dialogue scene, a rain chase in 21:9, a vertical runway walk at 1080p, a photo that speaks, a clay animation and a square product spot. Unmute any tile to hear it, then tap Use this prompt to make it your own.
A 12 s two-line exchange with native sound. She says "You came back." and he answers "I never really left." over the murmur of the bar, clinking glasses and rain on the glass. Start from this prompt for your own dialogue scene.
Medium two-shot, slow push in. In a candlelit wine bar at night, a strikingly beautiful woman in her late twenties with dark wavy hair and a green silk blouse leans across a small table toward a handsome man in his early thirties in a charcoal suit. She smiles and says warmly: "You came back." He sets down his glass, holds her gaze and answers softly: "I never really left." Warm amber candlelight, shallow depth of field, 35mm lens, soft film grain. Audio: low murmur of the bar, clinking glasses, gentle rain on the window, no music.
Cinemascope 21:9 action with real weight: every footstep throws a sheet of water through red and cyan neon, and you hear the rain, the splashes and his breathing. Start from this prompt for a chase or a music video moment.
Wide low tracking shot. A handsome man in his early thirties with short dark hair and a black leather jacket sprints down a flooded neon alley at night through heavy rain, every footstep throwing up sheets of water that catch red and cyan light, spray flying off his jacket. Anamorphic lens, teal and red grade, fine film grain. Audio: pounding rain, splashing footsteps, his heavy breathing, a roll of distant thunder.
A 1080p vertical fashion film for reels and shorts. The crimson silk ripples and pools across a mirror floor under one hard spotlight, cut to a pulsing bass beat and the clatter of shutters. Start from this prompt for a lookbook or a launch teaser.
Vertical low angle tracking shot. A strikingly beautiful woman in her late twenties with a sleek black bob strides down a glossy black runway toward camera in a flowing long sleeved crimson silk gown, the fabric rippling behind her in a strong wind, camera flashes popping from both sides. Hard white spotlight, mirror reflections on the floor, 50mm lens, editorial fashion film look. Audio: a deep pulsing bass beat, crowd murmur, rapid camera shutters.
Image to video from one picture: we made the harbor portrait first, then HeyGen Video 1.0 brought it to life. He turns, says "Every boat out there is someone coming home." and smiles, with gulls and lapping water around him. Start from your own photo the same way.
The camera pushes in slowly as the man turns his head toward the camera and a warm smile spreads across his face. He says in a calm, low voice: "Every boat out there is someone coming home." Mist drifts past the string lights behind him. Audio: gulls calling, water lapping against the pier, a distant ship horn, no music.
Stop motion charm in 4:3: the clay fox catches a snowflake, sneezes and says "Bless me!" with a tiny squeak, while felt smoke and cotton snow drift past. Start from this prompt for a holiday card or a kids' story.
Claymation with a stop motion feel, medium shot with a gentle push in. A round clay fox in a tiny knitted red scarf sits on a snowy miniature rooftop, catches a falling snowflake on its nose, sneezes, then grins and says brightly: "Bless me!" Felt chimney smoke, cotton snow drifting, warm glowing windows below, visible thumbprints in the clay. Audio: a tiny squeaky sneeze, soft wind, a distant chiming bell.
A square product spot made for feeds: a crash of ice cold water, flying droplets and bright lemon against black stone, with the pop, fizz and splash on the soundtrack. Swap in your own product and keep the light.
Extreme macro, slow orbit. A frosted glass bottle of sparkling lemon soda stands on wet black slate as a wave of ice cold water crashes over it, droplets bursting into the air and catching a hard white rim light, bright lemon slices tumbling past in slow motion. Glossy high contrast commercial look, 100mm macro lens, no text on the bottle. Audio: a crisp cap pop, fizzing bubbles, a bright splash, a deep whoosh, no music.
Why HeyGen Video 1.0 is made for talking scenes
Most video models give you a silent picture and leave the sound to you. HeyGen Video 1.0 makes the sound with the shot. Quote a line, say who says it and how, and it comes out of that character's mouth, with the room around them on the same track.
Our wine bar clip is two people and two lines in 12 s. She speaks first, he answers, and the bar murmur, glasses and rain sit under both voices. Our clay fox gets a squeaky sneeze and a two word line, and our runway walk gets a bass beat and camera shutters with no line at all.
It also starts from a picture. We made the harbor portrait on Pixel Dojo first, then gave it to HeyGen Video 1.0 with a line to say. The face, the coat and the string lights all hold, and he turns to camera and speaks.
What you can make with the HeyGen video model
Dialogue scenes with two speakers
Give each person one line and the order they speak in. For two lines, a 12 s clip gives each voice room to land, as in our wine bar scene.
Talking portraits from one photo
Upload a portrait, describe one move and quote a line. The clip keeps the face from your picture and follows its shape, so a 3:4 portrait stays 3:4.
Action with sound design
Rain, splashes and footsteps come with the picture. Our alley sprint throws water on every step and you hear each one land.
Stylized animation
Name the style first, such as claymation with a stop motion feel, and keep the sounds in that world: squeaks, chimes and soft wind.
Product spots for every feed
Pick 1:1 for feeds, 9:16 for reels, 16:9 for video and 21:9 for a cinematic banner. End the prompt with the sounds of the product: a pop, a fizz, a splash.
Long takes up to 30 seconds
One clip can run from a quick 5 s beat to a full 30 s scene. Raise the length for a longer script instead of packing more words in.
HeyGen Video 1.0 settings and what each one changes
- Length5 to 30 seconds
- Two short lines fit about 12 s. Set the length before you write the script.
- Resolution480p, 768p, 1080p, 2K
- Try an idea at 480p, then make the version you keep at 768p or above.
- Shape21:9, 16:9, 4:3, 1:1, 3:4, 9:16
- All six shapes work at 480p and 768p. At 1080p and 2K, pick 16:9 or 9:16.
- Start imageOne picture, optional
- With a picture, the clip takes its shape from the image. Use the prompt for motion, the line and the sound.
- SeedAny whole number
- Keep the seed and change one word to see exactly what that word does.
HeyGen Video 1.0 price by length and resolution
Credits per clip at list price, sound included. The tool shows the exact cost for your settings before you generate.
| Clip length | 480p | 768p | 1080p or 2K |
|---|---|---|---|
| 5 seconds | 3.75 | 6.25 | 15 |
| 10 seconds | 7.5 | 12.5 | 30 |
| 15 seconds | 11.25 | 18.75 | 45 |
| 30 seconds | 22.5 | 37.5 | 90 |
How to use HeyGen Video 1.0 on Pixel Dojo
- 1
Describe the shot
Open HeyGen Video 1.0 and start with the framing and camera move, then the person or object and one action.
- 2
Write the line
Put the exact words in quotes and say who speaks and how: warm, low, bright.
- 3
Name the sounds
End with an Audio line for ambience and effects. Add no music when you want only the room.
- 4
Pick length, size and shape
Choose 5 to 30 seconds, 480p to 2K and a shape, or add one picture to start from, then generate.
HeyGen Video 1.0 pricing on Pixel Dojo
HeyGen Video 1.0 is included in every Pixel Dojo plan, from $10/month, and it is priced per second of finished video with sound included.
480p is 0.75 credits a second, 768p is 1.25, and 1080p and 2K are 3 credits a second.
The clips on this page: 15 credits for the 12 s 768p dialogue scene, 15 credits for the 5 s 1080p runway walk, 6.25 credits for each 5 s 768p clip and 3.75 credits for the 5 s 480p soda spot. A full 30 s clip at 2K is 90 credits.
Commercial use is included on every plan, and the same credits work across every model on Pixel Dojo.
HeyGen Video 1.0 questions
What is HeyGen Video 1.0?
HeyGen Video 1.0 is HeyGen's first general video model. It turns a text prompt or one picture into a clip with sound: spoken lines you write in quotes, ambience and effects. You can use it on Pixel Dojo with every other top video model in one plan.
Does the HeyGen video model make sound and speak dialogue?
Yes. Every clip comes with sound. Put the words in quotes and say who speaks, and the character says them, as in our wine bar scene where two people trade a line each.
What lengths, resolutions and shapes does HeyGen Video 1.0 support?
Any length from 5 to 30 seconds at 480p, 768p, 1080p or 2K. At 480p and 768p you can pick 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. At 1080p and 2K you can pick 16:9 or 9:16.
Can I animate my own photo with HeyGen Video 1.0?
Yes. Add one picture as the start image and describe the motion, the line and the sound. The clip follows the shape of your picture, like our harbor portrait that turns and speaks.
How much does HeyGen Video 1.0 cost?
It is included in every Pixel Dojo plan, from $10/month. A 5 s clip is 3.75 credits at 480p, 6.25 credits at 768p and 15 credits at 1080p or 2K.
How do I use the HeyGen AI video generator on Pixel Dojo?
Open HeyGen Video 1.0, write the shot, the line in quotes and the sounds, pick length, resolution and shape, and generate. Developers can run the same model through the Pixel Dojo API.
Video Effects New
Your first video is free. One photo, one click.
310 ready-made effects, from AI Hug and Earth Zoom In to product spins and listing walkthroughs. Upload a photo and press Generate. No prompt to write, and a free account gets 3 a day.
Make your first HeyGen Video 1.0 clip
Write a prompt above or start from any example on this page. One plan covers every top model, six studios and Sensei, and your credits roll over.
Start with HeyGen Video 1.0