PixVerse V6 Max: 1080p video with synchronized native audio
PixVerse V6 Max turns a prompt or a single image into a 1080p clip up to 15 seconds long, with synchronized native audio generated in the same pass.
PixVerse V6 Max is the Max tier of PixVerse's V6 generation. It turns a text prompt or a single first frame into a clip of 1 to 15 seconds at up to 1080p, and it generates synchronized native audio in the same pass. Sound effects and ambience land on the frames where they belong. Text-to-video and image-to-video run through one model, so you can animate a photo or build a scene from scratch without a separate sound step.
ModelPixverse V6 Max15-second 1080p video with synchronized native audio.What it does well
Each example below was generated end to end at 1080p with audio on, so what you hear is matched to what you see.
Synchronized native audio
PixVerse V6 Max writes the soundtrack while it renders the video, so impacts, footsteps and ambience sit on the frames where they happen. Keep Generate Audio on and the clip comes back ready to review instead of silent. The streetball clip below ran at 1080p with audio on. The dribble bounces, sneaker squeaks and chain-net rattle all track the motion.
Camera moves from a text prompt
Name one camera move in the prompt and the model follows it, with or without an input image. The shot below used no first frame: it is text-to-video from the prompt alone, and the camera tracks alongside the runner toward the half-buried lander. Describe the move you want in plain terms, such as tracking, dolly, pan, tilt or orbit.
Examples to try
Start from a clear first frame of the standing row and let the chain play out. This image-to-video clip ran at 1080p with audio on, and the clacks stay synced as each tile falls.
The dominoes topple in a chain reaction down the curving row, each tile clacking as it knocks the next, until the final tile nudges the glass marble off the edge and it drops into the tin cup with a clink; the camera tracks the collapse.
The chain falls in sequence and the marble drops into the cup, clacks matched to the motion. A duration of 6 seconds suits a short chain like this one.
Recommended settings
| Setting | Value | When |
|---|---|---|
| Quality | 1080p | Finalize here; draft at 360p or 540p to iterate faster |
| Duration | 8s (1–15) | 5s for social, 8s to let an action play out, up to 15s for long-form |
| Generate Audio | true | For a finished, sound-matched clip; false for a silent draft |
| Aspect ratio | 16:9 or 9:16 | Landscape or vertical; an input image sets its own frame |
| Seed | Fixed integer | Pin it to reproduce an exact result |
Good to know
- Audio is generated only when Generate Audio is on. Leave it off when you want a quick silent draft.
- With an input image, the image sets the frame. The aspect ratio setting applies to text-to-video only.
- The model rewards literal prompts: name the subject, one action, one camera move and the exact sounds. Vague prompts vary between runs, so pin a seed to reproduce a result.
- Clips run 1 to 15 seconds at up to 1080p, with resolution options of 360p, 540p, 720p and 1080p.
Use it from the API
Send the same image-to-video call that produced the streetball clip above.
# pip install "segmind>=1.1.0"
# export SEGMIND_API_KEY="YOUR_API_KEY"
import segmind
result = segmind.run(
"pixverse-v6-max",
prompt="The player drives hard to the basket, crosses the ball low between his legs, plants his foot and rises for a one-handed layup; the ball rattles the chain net and drops through. Dribble bounces echo off the asphalt, his sneakers squeak on the court, and the chain net clatters.",
duration=8,
quality="1080p",
generate_audio_switch=True,
image_url="https://segmind-resources.s3.amazonaws.com/input/pixverse-v6-max-input-basketball.jpg",
aspect_ratio="16:9",
seed=20260330,
)
print(result.get("output"))# 1. Submit the request; the reply carries its request_id
REQUEST_ID=$(curl -s -X POST "https://api.segmind.com/v2/pixverse-v6-max" \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The player drives hard to the basket, crosses the ball low between his legs, plants his foot and rises for a one-handed layup; the ball rattles the chain net and drops through. Dribble bounces echo off the asphalt, his sneakers squeak on the court, and the chain net clatters.",
"duration": 8,
"quality": "1080p",
"generate_audio_switch": true,
"image_url": "https://segmind-resources.s3.amazonaws.com/input/pixverse-v6-max-input-basketball.jpg",
"aspect_ratio": "16:9",
"seed": 20260330
}' | jq -r .request_id)
# 2. Check its status until it is COMPLETED
curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID/status" \
-H "x-api-key: YOUR_API_KEY"
# 3. Fetch the result
curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID" \
-H "x-api-key: YOUR_API_KEY"Resources
- #image-to-video
- #text-to-video
- #pixverse
- #model-launch
- #audio
