WAN 2.1 MultiTalk creates speaking-character videos from an image and audio, combining lip synchronization with facial expressions and body gestures.
Model overview
- Model ID
wavespeed-ai/wan-2.1-multitalk- Output Type
- Avatar Video
- Pricing
- $0.03 / input second
- Provider
- WaveSpeed
- Hosting
- External
WAN 2.1 MultiTalk Talking avatar API example
curl -X POST https://api.protoface.com/v1/run/wavespeed-ai/wan-2.1-multitalk \
-H "Authorization: Bearer $PROTOFACE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"operation": "video.avatar",
"speech": "https://example.com/your-audio.wav",
"person": "https://example.com/your-image.png",
"prompt": "A red fox resting beside a woodland stream, soft morning light."
}'Supply a portrait image and prepared speech audio. Studio prepares speech from a script and selected voice without code. This request uses the selected mode and settings.
Supported modes
Talking avatar
Talking avatar uses script or audio and avatar. Adjust the model options to prepare a request for this mode.
video.avatarPricing
Price per input second. Round the total charge up to the next $0.01.
| Offering | Price (USD) |
|---|---|
| native | $0.03 |
- Round billed duration up to a whole second before calculating the charge.
- native: minimum billed duration 3s.
Talking avatar options
WAN 2.1 MultiTalk
WAN 2.1 MultiTalk turns a still image and an audio recording into an animated speaking performance. The image supplies the visual subject, and the audio drives synchronized mouth movement. Facial expression and body gestures contribute to the character’s delivery.
A text description can guide the scene and the subject’s pose or behavior while speech remains synchronized. This connects visual direction with the recorded performance, making the supplied voice an integral part of the animation.
What it's good for
Multitalk suits photo-based presenters for lessons, narrated announcements, and spokesperson material. Teams with an established character image and recorded narration can use those assets to create a visible presenter for their message.
Singing performances are another application: mouth movement follows the supplied vocal audio, giving a character image a musical delivery. For creative development, the combination of audio-driven animation and text-guided behavior supports testing how a character performs a script or song.
Run WAN 2.1 MultiTalk on Protoface
Use WAN 2.1 MultiTalk in Protoface Studio without writing code. Choose your inputs and generation settings, then generate with affordable, usage-based pricing. For your own AI app or workflow, use the Protoface API to submit generations and retrieve their outputs.

About WaveSpeed
WaveSpeed is an AI inference platform offering third-party generative models through developer APIs and creator applications. Its image and video workflows sit alongside WaveSpeed-branded media tools, including Video Face Swap, which takes source footage and a reference portrait to replace a selected face in a video.
- Media inference
- Creative tools
- Video face swap










