P Video Avatar
Generated on PixelDojo with P Video Avatar. Produced by PixelDojo's generation pipeline.
P Video Avatar costs 1 credit per second at 720p and 2 credits per second at 1080p, billed against the finished clip's duration. Our test on August 26, 2026 took about 35 seconds and returned a 5.56 second talking clip, so it charged around 5.6 credits. Here is the test we ran, since this model needs a specific kind of input to work at all.
The script we wrote and the clip it returned
Every example below was produced on PixelDojo. Hover to see the prompt.
Thanks for stopping by the harbor. The nets are mended and we head out at first light.
P Video Avatar
What the test showed
Why we used a portrait, not a product photo
The rest of this cost-and-speed series feeds the same earbuds product photo into every video model for a fair comparison. This model has no face to animate in that photo, so we swapped in a portrait instead and wrote a short original script for it to speak, since that is what the tool is actually built to do.
What the file measured out to
832 by 1088 pixels at the 720p setting, and 5.56 seconds long, timed to the script and the default voice. Resolution is a fixed 720p or 1080p choice rather than a free width and height.
Cost is billed on the finished duration
There is no duration field to set. The script's length (or the audio file's length, on the lip-sync path) determines how long the clip runs, and the per-second rate is applied to that after the fact.
How it differs from P Video
P Video takes a general prompt and any starting image, no face required, at half the per-second price on 720p. Reach for P Video Avatar specifically when the deliverable is a person talking.
How it differs from the P-Image stills
P-Image, P-Image Edit, and P-Image Ideogram only produce still images, from 0.1 to 0.5 credits. None of them add motion or speech, which is the entire reason this model exists.
The test: one portrait, one written script, no audio file supplied. Result: about 35 seconds, roughly 5.6 credits, a 5.56 second clip.
Why Choose Pixel Dojo for P Video Avatar
Professional-quality results with cutting-edge AI technology
It needs a face, not just any image
This is a portrait animator, not a general motion tool. The required input is an image field documented as a portrait to animate, and the whole feature set (voices, languages, lip-sync) only makes sense pointed at a face.
Two ways to drive the speech
Write a script and pick one of 30 named voices across 10 languages, or skip the script entirely and hand it an audio file to lip-sync to instead. We used the script-plus-voice path.
About 35 seconds for a 5.56 second clip
Fast for a video model. Our short script rendered in well under a minute, well inside the API's synchronous response window.
How It Works
How we ran this test:
Start with a real portrait
We picked a face-forward portrait from an earlier run in this series rather than a product photo, since the model has nothing to animate without a face.
Write a short, natural script
We kept the line to one sentence and let the default voice and language handle delivery, rather than tuning voice_prompt or video_prompt for this first test.
Read the clip length off the file, not the request
There is no duration input. The finished file ran 5.56 seconds because that is how long the script took to speak, and the credit charge follows that number.
Loved by creators on PixelDojo
Real feedback from people using PixelDojo, pulled from our in-product surveys.
THIS IS SO DOPE !
I have already recommended it to friends
All the tools, plus the guidance
Excellent tools. Ease of use. Well thought out interface. Wide variety of AI tools and features which are up to date with more added each month
I really like how the site is kept up to date, and the leaderboard (where I'm currently #11 most popular artist)
This is the best image generator I've used so far. Well done!
Explore more AI tools on PixelDojo
AI Tools
Compare & Switch
- Best AI Image Generators
- Best AI Video Generators
- Midjourney Alternatives
- Civitai Alternatives
- Runway Alternatives
- Leonardo Alternatives
- Pika Alternatives
- Luma Alternatives
- Magnific Alternatives
- Veo Alternatives
- Flux Alternatives
- Freepik Alternatives
- Seedance Alternatives
- Seedream Alternatives
- Pixverse Alternatives
- GPT Image Alternatives
- Synthesia Alternatives
- Playground Alternatives
- NightCafe Alternatives
- Canva AI Alternatives
- ElevenLabs Alternatives
- ComfyUI Alternatives
- Fal Alternatives
- Replicate Alternatives
Common Questions
Everything you need to know about P Video Avatar
How much does P Video Avatar cost?
1 credit per second at 720p, 2 credits per second at 1080p, charged against the finished clip's duration. Our 5.56 second test clip came to roughly 5.6 credits at 720p.
How fast is P Video Avatar?
About 35 seconds in our August 26, 2026 run, for a short script that produced a 5.56 second clip. There is no separate duration setting to speed it up or slow it down; the script length drives the render length.
What image do I need to use it?
A portrait with a visible face. We tried it against a product photo for consistency with our other tests and it does not apply there, since the whole feature set (voices, lip-sync, languages) is built around animating a face.
How is it different from P Video?
P Video accepts any starting image and a general motion prompt at 0.5 credits per second at 720p, no face required. P Video Avatar is 1 credit per second at 720p and only does one job: a portrait speaking a script or lip-synced to supplied audio.
Can I lip-sync it to my own audio instead of a script?
Yes. Supplying an audio file overrides the voice_script and voice fields entirely and the clip lip-syncs to that audio instead of synthesizing speech.
How do I call it from the API?
POST to /api/v1/models/p-video-avatar/run with your API key, an image URL, and either a voice_script or an audio URL. Same key and endpoint pattern as every other model in the catalog.