P-Video Avatar API, P-Video API - AI Video Generation APIs

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

LIMITED TIME OFFER

Get $5 Free Credit on First Payment

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

Claim Your $5 →

P Video Avatar Image to Video API Documentation

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

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 generate request to receive a POST callback instead of polling.

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

Request Parameters - P Video Avatar Generation

Parameter	Required	Type	Default	Description
image	Yes	string (URL)	—	Publicly accessible URL of the input image used as the first frame. Supported formats: jpg, jpeg, png, webp.
audio	No	string (URL)	—	Optional uploaded audio to drive lip-sync. If both `audio` and `voice_script` are provided, `audio` wins.
voice	No	string	"Zephyr (Female)"	Named voice for synthesized speech (used only when `audio` is not provided). Allowed values (30 total) — Female: 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: 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).
voice_language	No	string	"English (US)"	Output speech language. Allowed values: English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi.
voice_script	No	string	""	Script the person speaks (ignored if `audio` is set).
voice_prompt	No	string	"Say the following."	Style/tone/pacing/emotion guidance for the TTS engine.
video_prompt	No	string	"The person is talking."	Visual prompt describing the video.
resolution	No	string	"720p"	Output resolution. Allowed values: `720p`, `1080p`.
seed	No	integer	random	Random seed for reproducibility. Must be a non-negative integer (≥ 0).
disable_safety_filter	No	boolean	true	When `true`, skip the safety check on prompts and image.
disable_prompt_upsampling	No	boolean	false	When `true`, skip the multimodal prompt upsampler and pass the raw prompt through.
no_op	No	boolean	false	Health-check mode — returns status without running inference.
webhook	No	string (URL)	—	Gateway will POST the final result to this URL when the prediction reaches a terminal state.
webhook_events_filter	No	string[]	—	Restrict which events fire the webhook. Allowed values include `completed`, `failed`, `canceled`.

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 Image to Video API Pricing

Resolution	Duration	Price (USD)
720p	1s	$0.025
1080p	1s	$0.045

2. P Video v1

P Video v1 Text to Video API Documentation

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

Authentication

All requests require an API key passed via header.

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

Video Request - P Video

Request Code

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

{
  "prompt": "A cat walking in a garden"
}

import requests

url = "https://gateway.pixazo.ai/p-video/v1/p-video/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cat walking in a garden"
}

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

const url = 'https://gateway.pixazo.ai/p-video/v1/p-video/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  prompt: 'A cat walking in a garden'
};

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/v1/p-video/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cat walking in a garden"
  }'

Output

{
  "request_id": "p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

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

Request Parameters - Video Request

Parameter	Required	Type	Default	Description
prompt	Yes	string	—	Text prompt for video generation
image	No	string (URI)	—	Input image URL for image-to-video generation (jpg, jpeg, png, webp)
audio	No	string (URI)	—	Input audio URL to condition video generation (flac, mp3, wav)
duration	No	integer	5	Duration of the video in seconds (1-10). Ignored when audio is provided
aspect_ratio	No	string	"16:9"	Aspect ratio of the video. Ignored when image is provided
resolution	No	string	"720p"	Resolution: "720p", "1080p"
fps	No	integer	24	Frames per second: 24, 48
draft	No	boolean	false	Draft mode — generates a lower-quality preview faster
prompt_upsampling	No	boolean	true	Enhance the prompt for better results
disable_safety_filter	No	boolean	tru e	Disable safety filter for prompts and input image
save_audio	No	boolean	true	Save the video with audio
seed	No	integer	—	Random seed for reproducible generation
webhook	No	string	—	Webhook URL for async notifications when generation completes
webhook_events_filter	No	array	—	Event types to receive (e.g. ["completed"])

Example Request

{
  "prompt": "A cat walking gracefully through a sunlit garden with butterflies and flowers swaying in the breeze",
  "image": "https://example.com/cat.jpg",
  "audio": "https://example.com/garden-ambience.wav",
  "duration": 10,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "fps": 48,
  "draft": false,
  "prompt_upsampling": true,
  "disable_safety_filter": true,
  "save_audio": true,
  "seed": 42,
  "webhook": "https://your-webhook.com/callback",
  "webhook_events_filter": ["completed"]
}

Response

{
  "request_id": "p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Video Status - P Video

Request Code

POST https://gateway.pixazo.ai/p-video/v1/p-video/prediction
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "requestId": "12gkggc805rmw0cwmg9skrgcb8"
}

import requests

url = "https://gateway.pixazo.ai/p-video/v1/p-video/prediction"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "requestId": "12gkggc805rmw0cwmg9skrgcb8"
}

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

const url = 'https://gateway.pixazo.ai/p-video/v1/p-video/prediction';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  requestId: '12gkggc805rmw0cwmg9skrgcb8'
};

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/v1/p-video/prediction" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "requestId": "12gkggc805rmw0cwmg9skrgcb8"
  }'

Output

{
  "success": true,
  "id": "12gkggc805rmw0cwmg9skrgcb8",
  "status": "succeeded",
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/..."
}

Try Now

Request Parameters - Video Status

Parameter	Required	Type	Description
requestId	Yes	string	The prediction ID returned from the generate endpoint

Example Request

{
  "requestId": "12gkggc805rmw0cwmg9skrgcb8"
}

Response

{
  "success": true,
  "id": "12gkggc805rmw0cwmg9skrgcb8",
  "status": "succeeded",
  "input": {
    "prompt": "A cat walking in a garden",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "fps": 24,
    "duration": 5,
    "prompt_upsampling": true,
    "disable_safety_filter": true,
    "save_audio": true
  },
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/p-video/12gkggc805rmw0cwmg9skrgcb8_output_0.mp4",
  "created_at": "2026-02-28T11:47:49.377Z"
}

Request Headers

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

Response Handling

Common status codes for Video Status.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

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 and model validation errors.

Queue System Errors

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

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

Error via Status/Webhook

{
  "request_id": "p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "p-video",
  "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_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "p-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "p-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/p-video_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

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 of the output
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 v1 Text to Video API Pricing

Resolution	Duration	Price (USD)
720p	1s	$0.02
720p	1s	$0.005
1080p	1s	$0.04
1080p	1s	$0.01