One Portrait, One Audio Track, One Avatar Video
GoodAvatar turns one portrait and one voice track into one continuous talking avatar video. You do not need multiple photos, a shot list, or a stitching step.
The workflow is deliberately narrow: choose a portrait, add the audio, review the estimate, and let the task run in the background.
Why one portrait is enough
The video is built around a single face and a single voice track. That keeps the output consistent and avoids the seams that appear when separately generated segments are joined.
Use a portrait that shows the face clearly:
- Front-facing or slightly angled
- Even lighting, no strong shadows across the eyes
- No heavy beauty filters or extreme wide-angle distortion
- Face large enough to read expression
- JPG or PNG
The portrait must be AI-generated. A clean synthetic render reads better than a heavily retouched photograph, and real photographs are rejected before generation.
Why one audio track is enough
The complete track goes into one generation pass. The output is one clip, not a sequence of segments that need to be merged. The current single-track limit is 120 seconds.
For a first test, use 15-30 seconds. A 30-second clip usually takes about 10-15 minutes because generation runs at roughly 20-25 times the video length.
What the output is good for
Short presenter clips work well for:
- Product explainers
- Course introductions
- Sales follow-ups
- Help-center answers
- Social clips built from a repeatable script
It is not a replacement for a full editor. If you need scene changes, B-roll, or frame-level trimming, bring the GoodAvatar clip into your normal editing workflow.
Cost and next step
Video generation uses 5 credits per second. A 30-second clip uses 150 credits, about $1.69 at the Starter pack rate. New accounts include 100 credits for a first test.
If you want the pricing details, read pay-as-you-go pricing. If you already have a track, create your first video. If you are starting from a still photo, read photo to talking video.