P-Video Avatar API, P-Video API: Pricing, Documentation

P Video is an advanced AI video generation model offering multiple generation modes including text-to-video, image-to-video, audio-conditioned, and image+audio synthesis. Integrate seamlessly via the Pixazo API.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

P Video Avatar API Documentation

https://gateway.pixazo.ai/p-video-avatar/v1/p-video-avatar/generate

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

P Video Avatar Generation Request - P Video Avatar API

Request Code

POST https://gateway.pixazo.ai/p-video-avatar/v1/p-video-avatar/generate HTTP/1.1
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "voice": "Charon (Male)",
  "voice_language": "English (US)",
  "voice_script": "p-video is the fastest video model on earth!",
  "voice_prompt": "Say the following with a warm, confident tone.",
  "video_prompt": "A studio-lit talking head, soft key light, subtle camera movement.",
  "resolution": "1080p",
  "seed": 42
}

import requests

url = "https://gateway.pixazo.ai/p-video-avatar/v1/p-video-avatar/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
    "voice": "Charon (Male)",
    "voice_language": "English (US)",
    "voice_script": "p-video is the fastest video model on earth!",
    "voice_prompt": "Say the following with a warm, confident tone.",
    "video_prompt": "A studio-lit talking head, soft key light, subtle camera movement.",
    "resolution": "1080p",
    "seed": 42
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/p-video-avatar/v1/p-video-avatar/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  image: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png',
  voice: 'Charon (Male)',
  voice_language: 'English (US)',
  voice_script: 'p-video is the fastest video model on earth!',
  voice_prompt: 'Say the following with a warm, confident tone.',
  video_prompt: 'A studio-lit talking head, soft key light, subtle camera movement.',
  resolution: '1080p',
  seed: 42
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/p-video-avatar/v1/p-video-avatar/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
    "voice": "Charon (Male)",
    "voice_language": "English (US)",
    "voice_script": "p-video is the fastest video model on earth!",
    "voice_prompt": "Say the following with a warm, confident tone.",
    "video_prompt": "A studio-lit talking head, soft key light, subtle camera movement.",
    "resolution": "1080p",
    "seed": 42
  }'

Output

{
  "request_id": "p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "p-video-avatar",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "p-video-avatar",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - P Video Avatar Generation

Parameter	Required	Type	Default	Allowed values / range	Description
image	Yes	string (URL)	—	jpg, jpeg, png, webp	Publicly reachable URL of the portrait image used as the first frame of the video.
audio	Conditional	string (URL)	—	—	URL of an audio track the avatar lip-syncs to. Provide either `audio` or `voice_script`. If both are sent, `audio` wins and `voice_script` is ignored. The generated video length matches this audio.
voice	No	string	"Zephyr (Female)"	All 30 voices — Female (14): Zephyr (Female), Kore (Female), Leda (Female), Aoede (Female), Callirrhoe (Female), Autonoe (Female), Despina (Female), Erinome (Female), Laomedeia (Female), Achernar (Female), Gacrux (Female), Pulcherrima (Female), Vindemiatrix (Female), Sulafat (Female). Male (16): Puck (Male), Charon (Male), Fenrir (Male), Orus (Male), Enceladus (Male), Iapetus (Male), Umbriel (Male), Algenib (Male), Algieba (Male), Schedar (Male), Achird (Male), Zubenelgenubi (Male), Sadachbia (Male), Sadaltager (Male), Alnilam (Male), Rasalgethi (Male).	Named voice used to synthesize speech from `voice_script`. Ignored when `audio` is provided.
voice_language	No	string	"English (US)"	English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi	Language of the synthesized speech. Pair it with a `voice` that suits the persona. Ignored when `audio` is provided.
voice_script	Conditional	string	""	—	The script the avatar speaks, written in the target language. Required unless `audio` is provided. The video length is set by how long this speech is.
voice_prompt	No	string	"Say the following."	—	Delivery-style guidance for the speech (tone, pacing, emotion). Describe how the line is said, not what is said.
video_prompt	No	string	"The person is talking."	—	Visual guidance for body movement, framing and background behaviour. Avoid restating the script here.
negative_prompt	No	string	""	—	Things you do NOT want in the video, e.g. subtitles, text, blurry, low quality, watermark. Disabled when left empty.
strength_negative_prompt	No	number	0.5	0 – 4	How strongly the `negative_prompt` is applied. The optimal value can vary with the video length (experimental feature).
resolution	No	string	"720p"	720p, 1080p	Output video resolution. Iterate at `720p`, then re-run final assets at `1080p`.
seed	No	integer	random	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce a result; omit it for a different output each time.
disable_safety_filter	No	boolean	true	true, false	When `true` (the default), the safety checks on the prompts and input image are skipped. Set it to `false` to enforce them.
disable_prompt_upsampling	No	boolean	false	true, false	When `true`, your prompts are sent to the model exactly as written and the automatic prompt-enhancement step is skipped.
no_op	No	boolean	false	true, false	Health-check mode — validates the request and returns a status without running inference, so no video is produced.
webhook	No	string (URL)	—	HTTPS URL	Gateway will POST the final result to this URL when the request reaches a terminal state.
webhook_events_filter	No	string[]	—	completed, failed, canceled	Restricts which events trigger the webhook. Defaults to all terminal events.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Avatar image.
audio	1	MP3, WAV	Voice / audio track.

Example Request

{
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "audio": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/abhinav_YF5ZZmi6.mp3",
  "voice": "Charon (Male)",
  "voice_language": "English (US)",
  "voice_script": "p-video is the fastest video model on earth!",
  "voice_prompt": "Say the following with a warm, confident tone.",
  "video_prompt": "A studio-lit talking head, soft key light, subtle camera movement.",
  "resolution": "1080p",
  "seed": 42,
  "disable_safety_filter": true,
  "disable_prompt_upsampling": false,
  "no_op": false,
  "webhook": "https://your-server.com/webhooks/p-video-avatar",
  "webhook_events_filter": ["completed", "failed"]
}

Response

{
  "request_id": "p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors, model validation errors, and the shape returned via status/webhook.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance. Required: $0.01"
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'p-video-avatar' not found or is disabled"
}

Model Validation Errors (400)

// Missing or invalid fields — examples
{ "error": "image is required and must be a string URL" }
{ "error": "image must be a valid URL" }
{ "error": "voice must be one of: Zephyr (Female), Kore (Female), ... Rasalgethi (Male)" }
{ "error": "voice_language must be one of: English (US), English (UK), ..., Hindi" }
{ "error": "resolution must be one of: 720p, 1080p" }
{ "error": "seed must be a non-negative integer" }
{ "error": "voice_script must be a string" }
{ "error": "disable_safety_filter must be a boolean" }
{ "error": "Invalid webhook URL" }

Error via Status/Webhook

{
  "request_id": "p-video-avatar_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "p-video-avatar",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/p-video-avatar_019d42ce-ae71-7999-24c9-5d76447ecafb4"

Response (Completed)

{
  "request_id": "p-video-avatar_019d42ce-ae71-7999-24c9-5d76447ecafb4",
  "status": "COMPLETED",
  "model_id": "p-video-avatar",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/p-video-avatar_019d42ce-ae71-7999-24c9-5d76447ecafb4/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-01T07:13:45.138Z",
  "updated_at": "2026-05-01T07:14:32.000Z",
  "completed_at": "2026-05-01T07:14:32.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type (video/mp4)
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

P Video Avatar API Pricing — Per-Second Rates

Resolution	Price (USD)
720p	$0.025/sec
1080p	$0.045/sec

2. P Video v1

P Video v1 API Documentation

https://gateway.pixazo.ai/p-video/v1/p-video/generate