Skip to content

Wan

Wan 2.2 Speech to Video

No ratings yet
  • Studio: Avatar & lip sync
  • Makes: Video
  • Task: Talking avatar

Make a portrait talk or sing with Wan 2.2 Speech to Video. Pay per result with credits. No subscription.

Open in studio

from 48 credits

This model works on real people. You confirm you have their consent before you start.

Smiling young man talking to the camera in a warm studio
Example from the Avatar & lip sync studio, made with FLUX.2 Dev

What you can set

  • Prompt

    Text

    The positive prompt for the generation.

  • AudioRequired

    Upload an audio file

    The audio for generating the output.

  • ImageRequired

    Upload an image

    The image for generating the output.

  • Resolution

    Choice

    The resolution of the output video.

    • 480p (default)
    • 720p
  • Seed

    Number, repeats a result

    The random seed to use for the generation. -1 means a random seed will be used.

Reviews

From creators who made something with Wan 2.2 Speech to Video.

No ratings yet. Ratings come only from people who made something with this model.