PrunaAI/p-video-avatar
Pruna's talking head video generation model. Provide a portrait image and either a speech script or an audio file, and the model generates a realistic video of the person speaking. Supports multiple voices, languages, and output resolutions.
Try the model with a sample request using the same API shape shown in the reference page.
URL of an audio file to drive the talking head. Takes priority over voice_script when both are provided.. (Default: empty)
URL of the input portrait image (first frame). Supports jpg, jpeg, png, webp.
Script for the person to say when no audio is uploaded.. (Default: empty)
Voice for generated speech. Defaults to 'Zephyr (Female)'.
Output language for generated speech. Defaults to 'English (US)'.
Speaking style, tone, pacing or emotion instructions for the generated speech.. (Default: empty)
Optional prompt for the video.. (Default: empty)
Disable safety filter for prompts and input image. Defaults to true.
When true, skip the prompt upsampler and pass the raw user prompt to the video model.
URL of an audio file to drive the talking head. Takes priority over voice_script when both are provided.. (Default: empty)
URL of the input portrait image (first frame). Supports jpg, jpeg, png, webp.
Resolution of the generated video. Defaults to 720p.
Random seed for reproducible generation. (Default: empty)
Adjust settings and run the demo to see the model output generated here in real-time.
