infery
← All models
P Video Avatar

P Video Avatar

p-video-avatar

Video editby Prunaai

p-video-avatar generates talking-head videos from one portrait image plus a script or audio. 30 voices, 10 languages, 720p/1080p output. Run with an API.

Example

Details

Accepts
image + audio + video

Pricing

Price
3.13 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedintegerRandom seed. Set for reproducible generation.
audiostringOptional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings.
imagerequiredstringInput image (first frame). Supports jpg, jpeg, png, webp.
no_opbooleanHealth check mode - returns status without inference.
voiceenum: Zephyr (Female), Puck (Male), Charon (Male), Kore (Female), Fenrir (Male), Leda (Female)Voice to use when generating speech from voice_script.
resolutionstringenum: 720p, 1080p
video_promptstringOptional visual prompt describing how the person should appear or behave while speaking.
voice_promptstringOptional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken.
voice_scriptstringExact words the avatar should say. Required when no audio file is uploaded.
voice_languageenum: English (US), English (UK), Spanish, French, German, ItalianLanguage/accent target for generated speech.
negative_promptstringDisabled if empty.Mention what you do NOT want in the video, e.g. "subtitles, text, blurry, low quality, frames, watermark, titles, scene change". We recommend using multiple keywords at once.
disable_safety_filterbooleanDisable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation.
strength_negative_promptnumberStrength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature)
disable_prompt_upsamplingbooleanWhen true, skip automatic enhancement of the visual video prompt and use video_prompt directly.