ReplicateAudio to videoComing soon

prunaai/p-video-avatar

Name: prunaai/p-video-avatar
Brand: Replicate

prunaai/p-video-avatar is an audio to video tool from Replicate that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`image` required	URL or file	—	Input image (first frame). Supports jpg, jpeg, png, webp.
`seed`	number (whole)	—	Random seed. Set for reproducible generation.
`audio`	URL or file	—	Optional uploaded audio to drive avatar speech. If provided, this is used instead of voice_script and voice settings.
`no_op`	true or false	false	Health check mode - returns status without inference.
`voice`	JSON	Zephyr (Female)	Voice to use when generating speech from voice_script.
`resolution`	JSON	720p	Resolution of the video.
`video_prompt`	text	The person is talking.	Optional visual prompt describing how the person should appear or behave while speaking.
`voice_prompt`	text	Say the following.	Optional style instructions for how to speak voice_script, such as tone, pacing, accent, or emotion. These instructions are not spoken.
`voice_script`	text		Exact words the avatar should say. Required when no audio file is uploaded.
`voice_language`	JSON	English (US)	Language/accent target for generated speech.
`negative_prompt`	text		Disabled 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.
`strength_negative_prompt`	number 0 to 4	0.5	Strength of the Negative Prompt. Optimal value can differ for different video lengths (Experimental Feature)
`disable_prompt_upsampling`	true or false	false	When true, skip automatic enhancement of the visual video prompt and use video_prompt directly.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "prunaai/p-video-avatar",
    "input": {
      "image": "<image>"
    }
  }'