About the AI Avatar Maker
Turn a portrait plus an audio track into a talking avatar video, with mouth movement driven by the audio you supply. 2 models available right now.
How to use it
- Step 1
Upload a portrait
Provide the face that will be animated. A clear, front-facing photo gives the model the most to work with.
- Step 2
Add the audio track
Supply the speech or singing the avatar should perform. Mouth movement is driven by this audio.
- Step 3
Generate
The avatar video is rendered in the background and appears in your creations list when finished.
Models available in the AI Avatar Maker
- OmniHuman v1.5500 credits
- LTX 2.3700 credits
Model line-up and credit costs are read live from the platform and change as models are added or retired.
Frequently asked questions
- What do I need to make a talking avatar?
- Two things: a portrait image and an audio track. The model animates the portrait so the mouth movement follows the audio.
- Can I use my own voice recording?
- Yes. Any audio track you upload can drive the avatar. You can also generate speech first with the voice tools and use that as the input.
- How many credits does it cost?
- It depends on the model you pick — currently from 500 to 700 credits per run. Credits never expire: once they are in your account they stay there until you spend them.
- Who owns the talking avatar videos I generate?
- You do. Under the Floniks Terms of Service you own the outputs you generate with the Service, subject to those terms and your compliance with them.