PixVerse V6 Text to Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	pixverse-v6/text-to-video
Type	Video generation (text-to-video)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

PixVerse V6 text-to-video generates 1–15 second clips at 360p to 1080p from text, with 8 aspect ratios, optional synchronized audio, and style presets.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Clips with synchronized audio

Turn on generate_audio to get background music, sound effects, and dialogue in one generation.

generate_audioprompt

Multi-platform framing

Eight aspect ratios cover landscape, portrait, square, and ultra-wide formats.

aspect_ratioresolution

Stylized content

Use a style preset for anime, 3D animation, clay, comic, or cyberpunk looks.

style

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pixverse-v6/text-to-video",
  "input": {
    "prompt": "A street drummer in a rain-soaked neon alley plays a fast rhythm on overturned buckets, water splashing off each hit, crowd cheering in the background, handheld cinematic tracking shot",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": true,
    "resolution": "720p"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "pixverse-v6/text-to-video",
  "input": {
    "prompt": "A street drummer in a rain-soaked neon alley plays a fast rhythm on overturned buckets, water splashing off each hit, crowd cheering in the background, handheld cinematic tracking shot",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": true,
    "resolution": "720p"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "pixverse-v6/text-to-video",
  "input": {
    "prompt": "A street drummer in a rain-soaked neon alley plays a fast rhythm on overturned buckets, water splashing off each hit, crowd cheering in the background, handheld cinematic tracking shot",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": true,
    "resolution": "720p"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value pixverse-v6/text-to-video.

example pixverse-v6/text-to-video

input object required

Business parameters. Put PixVerse V6 Text to Video-specific configuration here.

prompt string required

Describes the scene, subject action, camera movement, and atmosphere of the video. 1–2048 bytes in UTF-8; each CJK character uses 3 bytes.

duration integer optional

Video length in seconds; any integer from 1 to 15.

default 5

resolution enum optional

Output video resolution: 360p, 540p, 720p, or 1080p.

default 720p enum: 360p540p720p1080p

aspect_ratio enum optional

Output video aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, or 21:9.

default 16:9 enum: 16:94:31:13:49:162:33:221:9

generate_audio boolean optional

Whether to generate background music, sound effects, and dialogue with the video.

default false

negative_prompt string optional

Content to avoid in the generated video. Up to 2048 bytes in UTF-8; each CJK character uses 3 bytes.

style enum optional

Visual style preset: anime, 3d_animation, clay, comic, or cyberpunk. Omit it to keep the model's natural look.

enum: anime3d_animationclaycomiccyberpunk

seed integer optional

Random seed. The same seed and prompt reproduce the same result.

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Neon alley bucket drummer

Text-to-video example at 16:9, 5 seconds, 720p with synchronized audio.

Request body

{
  "model": "pixverse-v6/text-to-video",
  "input": {
    "prompt": "A street drummer in a rain-soaked neon alley plays a fast rhythm on overturned buckets, water splashing off each hit, crowd cheering in the background, handheld cinematic tracking shot",
    "aspect_ratio": "16:9",
    "duration": 5,
    "generate_audio": true,
    "resolution": "720p"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated video from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

How is the prompt length limit counted?

Both prompt and negative_prompt are limited to 2048 bytes in UTF-8. Each English letter uses 1 byte and each CJK character uses 3 bytes.

What happens if I omit style?

The model keeps its natural look. Pass a value only when you want an anime, 3D animation, clay, comic, or cyberpunk style.

How is it billed?

See the live prices on the HiAPI pricing page. View pricing