Make a talking video
Wan-2.2 Speech-to-Video 14B
Wan-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements, and professional camera work for film and television applications
Opens the avatar studio with Wan-2.2 Speech-to-Video 14B ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Wan-2.2 Speech-to-Video 14B makes, what it needs and what you get
What it makes
Make a talking video
Turns a photo of a person and a voice recording into a video of that person speaking.
What you need
- A short description of the scene
- A photo of the person
- What they should say (an audio clip)
What you get
A video of the person speaking your audio
- resolutions up to 720p
About Wan-2.2 Speech-to-Video 14B
Wan-2.2 Speech-to-Video 14B turns a photo of a person and a voice recording into a video of that person speaking. It is made by Alibaba.
To use it, you provide a short description of the scene, a photo of the person and what they should say. You get a video of the person speaking your audio. Options include resolutions up to 720p.
A 5 s result costs about 5,000 credits. Longer or shorter results cost in proportion, about 1,000 credits per second. It is included from the Pro plan and up. You run it in the avatar studio, in your browser.
Best for
Typical uses for this kind of model.
- Presenters and explainer videos without filming
- Giving a character or mascot a voice
- Turning a recorded script into a video message
How to use Wan-2.2 Speech-to-Video 14B
- 1
Add a photo of the person and what they should say
Upload your files, or pick them from your library, then write a line about what you want.
- 2
Check the settings
Pick the options you want. The cost updates as you choose, and is shown before you generate.
- 3
Generate your video
A video of the person speaking your audio. Your result appears in the studio, ready to download.
Other models for this job
Same job: make a talking video. Compare before you choose.
Audio-driven talking avatar generation powered by the SoulX-FlashTalk 14B model.
Generate high-quality videos with UGC-like avatars from audio
EchoMimic V3 generates a talking avatar model from a picture, audio and text prompt.
LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.