Pixverse-6-T2V

PixVerse V6 · Text-to-Video

"V6 turns imagination into cinematic reality." Source: PixVerse.

PixVerse V6 is the sixth generation of PixVerse's video model, launched on 30 March 2026. It turns a text prompt into a video of up to 15 seconds, from 360p to 1080p, in eight aspect ratios from vertical 9:16 to cinematic 21:9, with native audio: dialogue, sound effects and ambient sound generated together with the picture.

It is the most flexible model in the catalog for format and budget: four resolutions, eight shapes, any length from 1 to 15 seconds, and audio you can switch off to pay less.

Pixverse/Pixverse-6-T2V

At a glance

Why PixVerse V6

• Sound that makes it feel finished. Dialogue, sound effects and ambient sound are generated with the frames, so the clip comes out close to final instead of silent.
• Up to 15 seconds at every resolution. Even at 1080p, one generation can hold a complete short idea, with fewer pieces to stitch.
• Eight shapes, including 21:9. Vertical for Reels and TikTok, square for the feed, widescreen for YouTube, and cinematic 21:9 for a film look.
• Four resolutions, one model. Draft at 360p, review at 540p, publish at 720p or deliver at 1080p.
• Pay only for what you need. Turn the audio off when you will add your own soundtrack, and the price per second drops.
• Better physics and emotion. PixVerse reports more realistic physical interactions between objects, more accurate camera movement, and character emotion that holds across frames more reliably than in previous releases.

Resolutions and aspect ratios

Each request selects one output resolution with resolution and one shape with aspect_ratio. Without them, the video is generated in 720p, 16:9.

Every aspect ratio is available at every resolution. Values are case-insensitive. The price depends on the resolution and on whether audio is on, not on the aspect ratio; the current rates are shown at the top of this page.

Video options

Every option is optional. An option you leave out takes its default.

Every length works at every resolution and aspect ratio.

A request with every option

{
  "model": "Pixverse/Pixverse-6-T2V",
  "prompt": "A cat in a tiny space suit floats through a starry sky, reaching for a glowing paper fish. Planets made of bread and balls of yarn drift past. Soft whimsical music, a gentle whoosh as the cat spins.",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "duration": 10,
  "generate_audio": true,
  "negative_prompt": "blurry, low quality, distorted limbs, text, watermark",
  "seed": 2026
}

Choosing the length

A longer clip needs a longer prompt. Describe what happens first, next and last, and what we hear, so the model has enough to fill the time.

Audio

With generate_audio on (the default), the video comes with dialogue, sound effects and ambient sound generated from your prompt. Write the sound into the prompt: what people say, what objects sound like, the music and the atmosphere.

Send "generate_audio": false when you will add music or a voice-over yourself. The video then has no audio track, and the price per second is lower.

Negative prompt

List what the video should avoid, separated by commas: blurry, low quality, distorted limbs, text, watermark. Use it for artifacts and for elements you want kept out of the scene.

Quick start

Video generation is synchronous: one request can keep the connection open for several minutes. Set a long client timeout (the examples use 15 minutes).

cURL

curl -X POST 'https://api.devupai.com/v1/video/generations' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -H "Content-Type: application/json" \
  --max-time 900 \
  -d '{
    "model": "Pixverse/Pixverse-6-T2V",
    "prompt": "A glowing jellyfish drifts through the deep ocean as a lone diver watches in awe. Shafts of blue light from above, slow bubbles, a deep calm ambient tone.",
    "resolution": "1080p",
    "duration": 8
  }'

A 15-second vertical clip with dialogue (cURL)

curl -X POST 'https://api.devupai.com/v1/video/generations' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  -H "Content-Type: application/json" \
  --max-time 900 \
  -d '{
    "model": "Pixverse/Pixverse-6-T2V",
    "prompt": "A young chef in a busy street kitchen in Algiers looks into the camera and says: \"Today, we make the perfect msemen.\" She folds the dough, drops it on a hot griddle and flips it as it sizzles. The street hums behind her, oil crackles, a pan clangs.",
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "duration": 15
  }'

A silent clip for your own soundtrack (Python)

import os
import requests

response = requests.post(
    "https://api.devupai.com/v1/video/generations",
    headers={
        "Authorization": f"Bearer {os.environ['DEVUP_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "Pixverse/Pixverse-6-T2V",
        "prompt": (
            "A cinematic aerial shot over a desert at dawn, long shadows across the dunes, "
            "a lone caravan of camels crossing the ridge."
        ),
        "resolution": "1080p",
        "aspect_ratio": "21:9",
        "duration": 12,
        "generate_audio": False,  # silent video, lower price per second
    },
    timeout=900,  # generation is synchronous and can take several minutes
)

result = response.json()
if response.status_code != 200:
    raise RuntimeError(result["error"]["message"])

# Download right away: the link expires 5 minutes after the response.
video_url = result["data"][0]["url"]
with open("desert.mp4", "wb") as f:
    f.write(requests.get(video_url, timeout=120).content)

print(result["_devup"])

Fast drafts at 360p (JavaScript, Node.js)

Explore several versions of an idea at the lowest resolution, then render the winner at 1080p with the same prompt and seed:

import { writeFile } from "node:fs/promises";

const prompt =
  "A ceramic coffee cup on a wooden table, steam curling up in the morning light. " +
  "The camera slowly pushes in. A spoon clinks softly.";

async function draft(seed) {
  const response = await fetch("https://api.devupai.com/v1/video/generations", {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.DEVUP_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      model: "Pixverse/Pixverse-6-T2V",
      prompt,
      resolution: "360p",
      aspect_ratio: "1:1",
      duration: 4,
      seed,
    }),
    signal: AbortSignal.timeout(900_000),
  });

  const result = await response.json();
  if (!response.ok) throw new Error(result.error.message);

  const video = await fetch(result.data[0].url);
  await writeFile(`coffee-${seed}.mp4`, Buffer.from(await video.arrayBuffer()));
  return result._devup;
}

console.log(await Promise.all([11, 22, 33].map(draft)));

Multipart

The same request can be sent as multipart/form-data, with every option as a text field:

curl -X POST 'https://api.devupai.com/v1/video/generations' \
  -H "Authorization: Bearer $DEVUP_API_KEY" \
  --max-time 900 \
  -F model="Pixverse/Pixverse-6-T2V" \
  -F prompt="A paper boat drifts down a rain-soaked street. Raindrops and distant thunder." \
  -F resolution="540p" \
  -F aspect_ratio="2:3" \
  -F duration="6"

Response

{
  "data": [
    {
      "url": "<video-url>"
    }
  ],
  "_devup": {
    "cost_dzd": "<cost_dzd>",
    "balance_dzd": "<balance_dzd>",
    "request_id": "req_<id>"
  }
}

• data[0].url is a signed link to the MP4. It expires 5 minutes after the response, so download the file right away rather than storing the link.
• _devup.cost_dzd is what the request cost, _devup.balance_dzd your remaining balance, and _devup.request_id the id to quote to support.

Receiving the video inline

Send "response_format": "b64_json" to receive the video Base64-encoded in data[0].b64_json. Only "url" and "b64_json" are accepted. A video larger than 20 MB is returned as a link instead, with a note in _devup.note; long 1080p clips often exceed 20 MB, so handle both shapes.

Billing

• You are billed per second of video actually generated, at the rate of the resolution you chose.
• Audio off costs less. With "generate_audio": false, the rate per second is lower at every resolution.
• Your balance must cover the length you request before the generation starts.
• Aspect ratio, negative prompt and seed do not change the price.
• Explore at 360p or 540p. Find the shot cheaply, then render the final at 720p or 1080p with the same prompt and seed.

Errors

Every option is checked before anything is generated. A value the model does not accept returns HTTP 400 with the code invalid_value, the message lists what is available, and nothing is charged.

A resolution the model does not offer:

{
  "error": {
    "message": "`4k` is not available for this model. Available: `360p`, `540p`, `720p`, `1080p`.",
    "type": "devup_error",
    "code": "invalid_value"
  }
}

A duration outside 1 to 15, or an aspect_ratio the model does not offer, also returns HTTP 400 invalid_value, and the message names the field and what to send. An input image is not accepted on this model, and returns HTTP 400 unsupported_content.

A request your balance cannot cover returns HTTP 402 before anything is generated.

Full reference: Text-to-video → Video options, Output resolution and Errors.

Writing prompts that work

1. Subject and action first. Who or what is in the frame, and what they do.
2. Name the shot and the camera. Wide shot, close-up, aerial, slow push-in, tracking shot.
3. Describe the light and the look. Golden hour, shafts of blue light, neon reflections, cinematic.
4. Write the sound. Quote the dialogue exactly, in quotation marks, and describe effects and ambience: oil crackles, a pan clangs, the street hums.
5. Give the scene a beginning, a middle and an end. It makes longer clips easier to fill and easier to judge.
6. Match the frame to the placement. Compose for 9:16 when the clip runs on Reels or TikTok, and for 21:9 when you want a film look.

Example

A glowing jellyfish drifts through the deep ocean as a lone diver swims closer, watching in awe. Shafts of blue light fall from the surface, slow bubbles rise. A deep, calm ambient tone and the soft sound of breathing through a regulator.

A production workflow

1. Explore at 360p, 4 to 5 seconds. Try several prompts and seeds in parallel at the lowest cost.
2. Fix the seed. Keep the seed of the version you like and refine the prompt around it.
3. Set the placement and the length. Choose the aspect_ratio for where the clip will run, and raise duration up to 15 seconds.
4. Decide on audio. Keep it on for a finished clip with sound; turn it off when you will add music or a voice-over, and pay less.
5. Render the final at 720p or 1080p. Same prompt, same seed, higher resolution.
6. Deliver. Download the MP4 within 5 minutes, or use b64_json and handle the link fallback.

About the model

PixVerse is a video generation company founded in 2023, which reports more than 100 million creators and enterprises using its products in 175 countries. It launched V6 on 30 March 2026, presenting it as a step forward in physical realism, camera accuracy, character emotion and native audio.

"V6 delivers complex scenes with coherent motion and consistent detail." Source: PixVerse.

PixVerse has not published the architecture, parameter count or a technical report for V6.

Source: PixVerse Launches V6.

Benchmarks

On the independent Artificial Analysis text-to-video arena with audio (AA-Video-T2V v2.1), where viewers compare two clips made from the same prompt without knowing which model made which, PixVerse V6 holds an Elo of 980 (95% confidence interval 965 to 995, 4,354 votes), ranked 21st of 31 models at the time of writing.

PixVerse V6 is not built to top the quality leaderboard: its strengths are range and control, with eight aspect ratios, four resolutions, any length up to 15 seconds and an audio switch that lowers the price. For the highest-rated clips with audio, see Wan 3.0 Video in the catalog.

Live leaderboard: Artificial Analysis text-to-video.

Best use cases

• Social content at every size: the same idea in 9:16, 1:1 and 16:9, with sound, for every platform.
• Short ads and talking clips: up to 15 seconds with dialogue and effects in one generation.
• Cinematic intros and banners: 21:9 for trailers, title sequences and website heroes.
• Silent B-roll: turn the audio off for footage you will score yourself, at a lower price.
• Low-cost exploration: many 360p drafts before a final render.

Limitations

• 15 seconds maximum per generation, and 1080p maximum resolution.
• Text-to-video only. To animate your own image, see PixVerse V6 Image-to-Video and the other image-to-video models in the catalog.
• One continuous clip per request. Multi-shot generation is not available on DEVUP AI yet.
• Generated dialogue may not be exact. Check spoken words and lip movement before publishing.
• Generative video models can reflect societal biases and produce inappropriate content. Review prompts and outputs before publishing.

Resources

• PixVerse V6 on PixVerse
• PixVerse Launches V6 (announcement)
• PixVerse Platform Docs: V6 released
• Artificial Analysis: text-to-video leaderboard
• DEVUP AI text-to-video documentation