# PixVerse V6 Text to Video

PixVerse V6 transforms prompts into high-quality videos with synchronized audio, supporting multiple aspect ratios, single or multi-clip storytelling, and enhanced prompt understanding for more accurate and dynamic results.

## API Information

- **Model Slug:** pixverse-v6-text-to-video
- **Branded URL:** https://www.eachlabs.ai/pixverse/pixverse-v6/pixverse-v6-text-to-video
- **Provider:** PixVerse
- **Category:** Text to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing scales with quality and audio:• 360p — $0.025 / $0.035 (no audio / with audio)• 540p — $0.035 / $0.045• 720p — $0.045 / $0.060• 1080p — $0.090 / $0.115Example: a 5-second 720p clip with no audio = $0.225.
- **Estimated Processing Time:** 90 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/pixverse-v6-text-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing scales with quality and audio:• 360p — $0.025 / $0.035 (no audio / with audio)• 540p — $0.035 / $0.045• 720p — $0.045 / $0.060• 1080p — $0.090 / $0.115Example: a 5-second 720p clip with no audio = $0.225.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing scales with quality and audio:• 360p — $0.025 / $0.035 (no audio / with audio)• 540p — $0.035 / $0.045• 720p — $0.045 / $0.060• 1080p — $0.090 / $0.115Example: a 5-second 720p clip with no audio = $0.225. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt describing the desired video content. Max 2048 characters. |
| aspect_ratio | string | Yes | 16:9 | - | Aspect ratio of the output video. Options: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9. |
| resolution | string | No | 720p | - | Video resolution. Alias for quality. 720p is recommended for most use cases. |
| duration | string | Yes | 5 | - | Duration of the output video in seconds. V6 supports 1-15 seconds (including 1080p). |
| seed | integer | No | - | - | Random seed for reproducible results. Range: 1-2147483647. |
| generate_audio_switch | boolean | No | false | - | Enable automatic audio generation for the video. Default: false. |
| generate_multi_clip_switch | boolean | No | false | - | Multi-clip generation mode. true: multi-clip, false: single-clip. Default: false. |
| thinking_type | string | No | auto | - | Prompt reasoning mode: enabled, disabled, or auto. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "pixverse-v6-text-to-video",
  "input": {
    "prompt": "A cinematic shot of a motorcyclist riding along a coastal road during sunset. The sky is filled with vibrant orange, pink, and purple hues, reflecting on the ocean beside the road. The camera smoothly tracks from the side, capturing the silhouette of the rider against the glowing horizon. The motorcycle moves steadily, wind flowing through the rider’s clothes and helmet reflections catching the sunlight. Waves softly crashing in the background. Warm golden light, dramatic shadows, lens flare, ultra realistic, 4K, shallow depth of field, cinematic color grading, smooth motion, powerful and emotional atmosphere.",
    "aspect_ratio": "16:9",
    "duration": "10"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**PixVerse | V6 | Text to Video Overview**

PixVerse | V6 | Text to Video transforms detailed text prompts into high-quality videos up to 1080p resolution and 15 seconds long, solving the challenge of creating professional-grade short-form content without complex editing. Developed by PixVerse, a Singapore-based AI video platform founded in 2023, this model stands out with its single-pass generation of multi-shot storytelling, native synchronized audio, and cross-frame facial emotion consistency. The primary differentiator is its ability to produce seamless 15-second 1080p videos in one generation, eliminating clip-stitching artifacts common in earlier models. Ideal for creators needing cinematic outputs with precise camera controls and realistic physics, PixVerse | V6 | Text to Video powers marketing clips, social media reels, and product demos directly from text or images on each::labs. Access it via the PixVerse | V6 | Text to Video API for streamlined integration.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.