Models / Wan-AI
Video

Wan 2.7 Text-to-Video

Text-to-video generation with native 1080p output, optional audio input, and multi-shot narrative control

About model

Wan 2.7 Text-to-Video is a dedicated generation model for creating 720P or native 1080P video directly from text prompts. It features optional audio input, multi-shot narrative control through prompt language, and output durations from 2 to 15 seconds.

Duration

2-15s

Supported generation length

Resolution

720P / 1080P

Supported output tiers

Input Modality

Audio

Optional audio input

Model key capabilities
  • Text-to-Video: Generate 720P or 1080P video directly from text prompts
  • Audio Support: Optional audio input with auto-generated background audio when absent
  • Narrative Control: Multi-shot narrative control through prompt language
  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    Wan-AI/Wan2.7-T2V

    curl --request POST \
      --url https://api.together.xyz/v2/videos \
      --header "Authorization: Bearer $TOGETHER_API_KEY" \
      --header "Content-Type: application/json" \
      --data '{
        "model": "Wan-AI/Wan2.7-T2V",
        "prompt": "some penguins building a snowman"
      }'
    
    from together import Together
    
    client = Together()
    
    # Create a video generation job
    job = client.videos.create(
        prompt="A serene sunset over the ocean with gentle waves",
        model="Wan-AI/Wan2.7-T2V"
    )
    
    import Together from "together-ai";
    
    const together = new Together();
    
    async function main() {
      // Create a video generation job
      const job = await together.videos.create({
        prompt: "A serene sunset over the ocean with gentle waves",
        model: "Wan-AI/Wan2.7-T2V"
      });
    
  • Model card

    Architecture Overview:
    • Text-to-video (T2V) generation model
    • 720P and native 1080P output

    Performance Characteristics:
    • Supports 2-15 second generation

  • Prompting

    Together AI API Access:
    • Access Wan 2.7 Text-to-Video via Together AI APIs using the endpoint Wan-AI/Wan2.7-t2v
    • Authenticate using your Together AI API key in request headers
    • Available on Together AI serverless infrastructure

  • Applications & use cases

    Creative Production:
    • Generate 720P or native 1080P video directly from text prompts for campaign content, product videos, and creative prototyping

Related models
  • Model provider
    Wan-AI
  • Type
    Video
  • Resolution/Duration
    720p, 1080p / 2-15s
  • Deployment
    Serverless
  • Price

    $0.10 / video

  • Input modalities
    Text
    Audio
  • Output modalities
    Video
  • Category
    Video