# Wan 2.7 T2V - Core.Today AI API

> Alibaba Wan 2.7 text-to-video model. Supports up to 15 seconds, audio synchronization for voice/music, multilingual prompts, and prompt expansion, at 720p or 1080p.

- **Provider**: Alibaba
- **Model ID**: wan-video/wan-2.7-t2v
- **Category**: Video Generation
- **Credits**: 1740 per second, tiered by resolution
- **Speed**: Medium
- **Quality**: High

## Features
- Text-to-video generation up to 15 seconds
- Audio synchronization for voice and music (auto-generated or user-supplied)
- Multilingual prompt support
- Automatic prompt expansion for short prompts
- 720p/1080p output with multiple aspect ratios

## Use Cases
- Multilingual voice-synced marketing or narration clips
- Music-video style content with synchronized audio
- Longer-form (up to 15s) narrative shots from a single prompt
- Rapid prototyping using short prompts with automatic expansion

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for video generation

### Optional
- **negative_prompt**: string - Negative prompt — describes content that should not appear in the video
- **audio**: string - Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization. If not provided, the model auto-generates matching audio.
- **resolution**: string (default: 1080p) - Output video resolution
  Options: 720p, 1080p
- **aspect_ratio**: string (default: 16:9) - Aspect ratio of the generated video
  Options: 16:9, 9:16, 1:1, 4:3, 3:4
- **duration**: integer (default: 5) - Duration of the generated video in seconds
- **enable_prompt_expansion**: boolean (default: true) - Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency.
- **seed**: integer - Random seed for reproducible generation. Range: 0-2147483647

## Examples

### Multilingual voice-synced clip
Generate a video with dialogue synchronized to an uploaded audio track.
```json
{
  "model": "wan-video/wan-2.7-t2v",
  "input": {
    "prompt": "A chef in a busy kitchen explains a recipe while chopping vegetables, warm natural lighting.",
    "audio": "https://example.com/narration-ko.mp3",
    "resolution": "1080p",
    "duration": 8
  }
}
```

### Auto-generated audio from a short prompt
Let the model expand a short prompt and auto-generate matching audio.
```json
{
  "model": "wan-video/wan-2.7-t2v",
  "input": {
    "prompt": "A drummer performing an energetic solo on stage.",
    "enable_prompt_expansion": true,
    "resolution": "720p",
    "duration": 5
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Leave `audio` empty to let the model auto-generate matching sound instead of sourcing your own track.
- Keep `enable_prompt_expansion` on for short prompts — it improves quality at the cost of some latency.
- Duration can go up to 15 seconds — longer clips are billed proportionally more at the per-second rate.
- Use `negative_prompt` to steer away from unwanted artifacts like text overlays or watermarks.

## Documentation
https://replicate.com/wan-video/wan-2.7-t2v