Name: Alibaba Wan 2.7 Text-to-Video Generator API
Brand: magicapi
SKU: api-magicapi-text-to-video-generator-wan-video-wan-2-7-t2v
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Text-to-Video Generator API (Alibaba Wan 2.7)

## Overview
Wan 2.7 Text-to-Video is Alibaba's video model that turns a text prompt into a video with audio. Its developer describes it as generating 1080p video of up to 15 seconds with audio synchronization.

Send a text `prompt` and a `duration` of 2 to 15 seconds. Optionally send an `audio` file for the video to sync to; without one, the model generates matching audio itself. Each request returns the URL of one MP4 video.

## Features
- **2 to 15 second videos**: set `duration` in whole seconds (default 5).
- **720p or 1080p**: `resolution` defaults to `1080p`.
- **Five aspect ratios**: `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`.
- **Audio**: the model generates matching audio when you send no `audio`. Send a wav or mp3 file (3 to 30 seconds, up to 15 MB) to sync the video to your own voice or music.
- **Prompt expansion**: `enable_prompt_expansion` (default `true`) expands and optimizes the prompt; it helps short prompts but adds latency. Set it to `false` to use your prompt as written.
- **Negative prompt**: describe content that should not appear with `negative_prompt`.
- **Seed**: set a seed (0 to 2147483647) to reproduce a result.

## Use Cases
1. **Social clips**: short vertical (`9:16`) or square (`1:1`) videos with sound from a one-line idea.
2. **Ads and product teasers**: 5 to 15 second 1080p shots in `16:9`.
3. **Music and voice-driven videos**: send your own audio track and generate a video that follows it.
4. **Storyboards and previews**: quick 720p drafts of a scene before a final render.

## Visual Examples
### Example Input
Prompt: "A cat sitting on a windowsill watching rain fall outside"

Settings: `duration` `2`, `resolution` `720p`, `aspect_ratio` `16:9`, `enable_prompt_expansion` `false`, `seed` `99999`. No `audio` was sent, so the model generated the audio.

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/11/wan-2-7-t2v-output-n7deb4jh-api-market.mp4) (2 seconds, 720p, 16:9)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt for video generation |
| `negative_prompt` | string | No | `""` |  | Negative prompt; describes content that should not appear in the video |
| `audio` | string (URL) | No | none |  | Audio file (wav/mp3, 3-30s, up to 15 MB) for voice/music synchronization. If not provided, the model auto-generates matching audio |
| `resolution` | string | No | `1080p` | `720p`, `1080p` | Output video resolution |
| `aspect_ratio` | string | No | `16:9` | `16:9`, `9:16`, `1:1`, `4:3`, `3:4` | Aspect ratio of the generated video |
| `duration` | integer | No | `5` | 2 to 15 | Duration of the generated video in seconds |
| `enable_prompt_expansion` | boolean | No | `true` |  | Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency |
| `seed` | integer | No | none |  | Random seed for reproducible generation. Range: 0-2147483647 |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.12 per API unit.
- **1 API unit = 1 second of output video, billed on the requested `duration`.** `resolution`, `aspect_ratio` and audio do not change the price.

| `duration` | API units | Price per request |
| --- | --- | --- |
| 2 seconds (minimum) | 2 | $0.24 |
| 5 seconds (default) | 5 | $0.60 |
| 10 seconds | 10 | $1.20 |
| 15 seconds (maximum) | 15 | $1.80 |

- **Example cost**: the example requested a 2 second video, so it cost 2 units, $0.24.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/text-to-video-generator-wan-video-wan-2-7-t2v`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 2 seconds and an overall timeout of 900 seconds (15 minutes) work well. The 2 second 720p example took about 36 seconds; longer and 1080p videos take longer.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/text-to-video-generator-wan-video-wan-2-7-t2v/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "wan-video/wan-2.7-t2v",
    "input": {
      "seed": 99999,
      "prompt": "A cat sitting on a windowsill watching rain fall outside",
      "duration": 2,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "enable_prompt_expansion": false
    }
  }'
```

Response (201 Created):
```json
{
  "id": "n7deb4jhqdrmw0d1mvqv23j410",
  "version": "wan-video/wan-2.7-t2v",
  "status": "starting",
  "created_at": "2026-11-04T14:21:04.315Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/text-to-video-generator-wan-video-wan-2-7-t2v/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "n7deb4jhqdrmw0d1mvqv23j410",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/wan-2-7-t2v-output-n7deb4jh-api-market.mp4",
  "error": null,
  "created_at": "2026-11-04T14:21:04.315Z",
  "started_at": "2026-11-04T14:21:04.337Z",
  "completed_at": "2026-11-04T14:21:40.668Z"
}
```

`output` is a single URL string pointing to the generated MP4 video.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt`, a `duration` outside 2 to 15 or a `resolution` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/text-to-video-generator-wan-video-wan-2-7-t2v";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "wan-video/wan-2.7-t2v", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 900000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 15 minutes");
}

createAndWaitForPrediction({
  "seed": 99999,
  "prompt": "A cat sitting on a windowsill watching rain fall outside",
  "duration": 2,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "enable_prompt_expansion": false
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/text-to-video-generator-wan-video-wan-2-7-t2v"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "wan-video/wan-2.7-t2v", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 900
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 15 minutes")


print(create_and_wait_for_prediction({
    "seed": 99999,
    "prompt": "A cat sitting on a windowsill watching rain fall outside",
    "duration": 2,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": False
}))
```

## FAQ
- **Does the video have sound?**
  - Yes. Without an `audio` input the model generates matching audio. Send your own wav or mp3 (3 to 30 seconds, up to 15 MB) as `audio` to sync the video to it.
- **Does 1080p cost more than 720p?**
  - No. Every second costs $0.12 at both resolutions and every aspect ratio.
- **How is the price of a request calculated?**
  - `duration` seconds times $0.12. The default 5 second video costs $0.60 and the 15 second maximum costs $1.80.
- **Why does the result differ from my prompt?**
  - `enable_prompt_expansion` is `true` by default and rewrites the prompt before generation. Set it to `false` to use your prompt as written, as in the example.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Turn a text prompt into a 2 to 15 second 720p or 1080p video with generated or synced audio using Alibaba's Wan 2.7. $0.12 per second of video, pay as you go.