1. Home
  2. AI models
  3. Wan 2.7
Video model by Alibaba

Wan 2.7

Makes a character speak in time with a recorded voice line, or keeps the cast the same from reference pictures.

What it is
Video model with lip-sync
Made by
Alibaba
Clip length
2 to 15 seconds
Sound
Moves the mouth to a recorded voice line
Starts from
The shot's first frame, or words alone
Cast pictures
Up to 5, to keep people the same
Price
4 tokens a second
Real results from Wan 2.7Made by us with this model, not picked from the maker's showreel. Clips are shown smaller than the model makes them
Lip-synced to a recorded voice

The shot: Cold blue dusk, whitecaps crashing on black rocks, a lighthouse beam sweeping overhead. A weathered woman in her late fifties in a cream cable-knit sweater picks her way along the shore and stops, her eyes narrowing at a glint of green glass between two rocks. Slow push in. She says: “Twenty years I've kept this light. Maybe it's time it kept itself.”

What Wan 2.7 is

Wan 2.7 is the model the AI Video Studio uses when a person has to talk and look real. The voice line is recorded first and the model moves the mouth to match it. It can also hold up to five cast members from their pictures.

Strengths and weaknesses

No model is best at everything. This is where Wan 2.7 earns its place, and where another model will serve you better.

Where it is strong

  • The mouth follows a real voice track, so the voice is the one you cast.
  • Holds a face well. In our test the woman is the same person from the wide shot to the close-up.
  • Clips from 2 to 15 seconds.

Where it falls short

  • It has no sound of its own. Without a voice line the clip is silent.
  • Four tokens a second.
  • Wan 3.0 is newer and makes its own sound for the same price.

Best for

  • Talking shots with a chosen voice
  • Scenes where the cast must match their pictures

Pick another model when

  • You want sound and speech made with the pictureWan 3.0 →
These notes come from our own runs in the studio: the same prompt on every model, and the films and designs we have made with them.

Where you can use it

One place in the studio runs this model. The link opens the tool; the price is shown again before anything is charged.

AI Video Studio4 tokens a second (20 tokens for 5 seconds)Open the Video Studio
Tokens come from a monthly plan or a one-off pack. See pricing.

Questions

Something else? Ask us.

How much does Wan 2.7 cost on ideahits?

Wan 2.7 costs 4 tokens a second (20 tokens for 5 seconds) in AI Video Studio. You pay with tokens from one balance that works on every model, and the price is shown before each run. A run that fails is refunded.

What is Wan 2.7 best for?

Talking shots with a chosen voice; Scenes where the cast must match their pictures. Consider Wan 3.0 when you want sound and speech made with the picture.

Do I need an account with Alibaba to use Wan 2.7?

No. Wan 2.7 runs inside the ideahits studio. One ideahits account and one token balance cover every model here.

Can I use what Wan 2.7 makes for commercial work?

Yes. What you make in the studio is yours to use, including in adverts, on products and for clients.

Try Wan 2.7.

Create an account, pick a pack from $6, and drop in a picture.

10 free tokens to start