How to make talking avatar and lipsync videos in Sume Studio
Make a photo talk, sync new audio to a video or build an AI influencer in Sume Studio, with lipsync and avatar models from Kling, ByteDance, VEED and others.
To make a talking avatar or lipsync video, start from a face, either a photo or a video, add the voice or script, and run a lipsync model that moves the mouth to the audio. Sume Studio does this by hand from one prompt bar, with the same models Sume's agents use (Studio).
Studio's tabs include Lipsync, Face swap and AI Influencer, next to Image, Video, Audio and Music, and every result is saved to your assets.
Which models can you use?
The lipsync and avatar models Sume runs are listed on the models page, each with its own page. They include Kling Avatar 2.0, OmniHuman 1.5, VEED Fabric 1.0, InfiniTalk, Sync Lipsync and Kling Lipsync.
| You have | Use |
|---|---|
| A photo and audio | A photo-to-talking-video model, such as Kling Avatar or OmniHuman |
| A video and new audio | A video lipsync model, such as Sync Lipsync or Kling Lipsync |
| A character to reuse | AI Influencer in Studio |
What about Sume Avatar 1.0?
Earlier Sume guides covered Avatar 1.0, a talking-head endpoint on the older developer API. Avatar and lipsync video are now made in Studio with the models above, or called from the Sume API.
Sources
Related posts
More in Models
- 4K AI video generation API: resolutions by model, 360p to 4K
For 4K on Sume, pin gemini-omni-flash-1.1 with resolution 4K; minimax-h3 upscales to 2K or 4K. Resolutions for every video model, and the price effect.
- AI video generation API length limits: up to 30 seconds per clip
On Sume, seedance-2.5 (4–30 s) and wan-3.0 (2–30 s) make 30-second clips; other models stop at 15 s or less. Limits by model, the error, and going longer.
- Gemini Omni Flash 1.1 API: text, image, and reference video modes
Call Gemini Omni Flash 1.1 on Sume as gemini-omni-flash-1.1: text, image, or reference to video, 3–10 second clips from 360p to 4K, with native audio.
- Lip sync API: turn an image and audio into a talking clip
Send a still image and Sume-hosted audio to VEED Fabric 1.0 or MiniMax H3 Max Lip Sync and get a talking clip back. Inputs, limits, and per-second pricing.
Written by Sume