Video model by AlibabaWan family live

Wan 2.2 Speech-to-Video on CraftyPeak

Animate a portrait to your own voice track.

Wan 2.2 Speech-to-Video (S2V) is Alibaba's audio-driven model: give it an image and an audio track, and it animates the character to speak or sing in sync.

Try Wan 3.0 now Browse video models

Premium platform. Cheaper pricing.

CraftyPeak passes provider savings straight to you, so every model is priced to undercut big platforms like Higgsfield and Runway.

An alternative to Higgsfield, Runway, OpenArt and HeyGen.

The Wan family is live on CraftyPeak

Wan 2.2 Speech-to-Video itself is on its way. Wan 3.0 from the same family is ready in the CraftyPeak prompt bar today, along with these models:

On PeakBrush

Wan 2.2 Speech-to-Video for digital artists

When Wan 2.2 Speech-to-Video goes live in CraftyPeak, digital artists on PeakBrush can use it to animate finished artwork into a short showcase clip. Until then, the models below are ready today.

Try Wan 3.0 now

Features

What Wan 2.2 Speech-to-Video does

Wan 2.2 S2V turns a still image and an audio track into a talking or singing video, with lip and body movement driven by the sound.

You are on PeakBrush. AI video and image generation in the Peakime ecosystem happens in CraftyPeak. When Wan 2.2 Speech-to-Video goes live, you pick it in the CraftyPeak prompt bar and CraftyPeak runs it for your generation.

  • Audio-driven

    Lip and body movement follow your audio.

  • Speech and song

    Works for dialogue and singing.

  • From one image

    Animate a single portrait or character.

  • Open weights

    Part of the Wan 2.2 family.

It is part of the open Wan 2.2 family.

Specifications

Wan 2.2 Speech-to-Video at a glance

As announced by Alibaba. Live CraftyPeak prices and limits appear here when Wan 2.2 Speech-to-Video is in the prompt bar.

Inputs
Image plus audio track
Sound
Uses your audio
Released
August 2025

Only on CraftyPeak

Wan 2.2 Speech-to-Video, the CraftyPeak way

The model is the engine. CraftyPeak is the studio around it: when Wan 2.2 Speech-to-Video lands in the prompt bar, it plugs straight into everything below.

Use cases

Made for

  • Talking avatars
  • Music performances
  • Explainers with a presenter
  • Podcast visuals

Prompt tips

Get better results

  1. 1Use a clean, front-facing portrait.
  2. 2Supply clear audio with little background noise.
  3. 3Keep the framing to head and shoulders for lip sync.

Switching

An alternative to Higgsfield, Runway, OpenArt and HeyGen

Looking for a Higgsfield, Runway, OpenArt or HeyGen alternative? CraftyPeak AI gives you one credit wallet for every video and image model, and Wan 2.2 Speech-to-Video joins the line-up as soon as it is available.

  • Higgsfield alternative
  • Runway alternative
  • OpenArt alternative
  • HeyGen alternative
  • Krea alternative
  • Freepik alternative
  • fal.ai alternative
  • Pollo AI alternative
  • Pika alternative
  • Hailuo alternative
  • Kling AI alternative
  • Leonardo AI alternative

Also known as

Wan 2.2 S2V · Wan2.2-S2V-14B · Wan speech to video

FAQ

Questions, answered

Is CraftyPeak AI an alternative to Higgsfield, Runway, OpenArt and HeyGen?

Yes. CraftyPeak AI runs video and image models in one credit wallet with pay-per-use pricing. Wan 2.2 Speech-to-Video is coming; the models linked on this page are available today.

Does Wan 2.2 S2V make its own voice?

No. It animates to the audio you supply.

When will Wan 2.2 Speech-to-Video be on CraftyPeak AI?

It is on the way. This page switches to live prices and a Generate button as soon as Wan 2.2 Speech-to-Video is in the prompt bar.

Available now

Create today on CraftyPeak

CraftyPeak by Peakime

The Wan family is live on CraftyPeak by Peakime

Wan 2.2 Speech-to-Video is on its way. Today you can generate with Wan 3.0 from 5 credits a second ($0.05), at cheaper prices, from one credit wallet with no subscription tier to pick.

Try Wan 3.0 now Browse all models