live

MODEL IDprunaai:p-video@2-pro-avatar

P-Video-2-Pro-Avatar

by October 22, 2026

P-Video-2-Pro-Avatar is Pruna AI's talking-video model that turns a single portrait into a lip-synced video driven by an uploaded audio track or a script read by built-in text-to-speech. Lips and expression follow the soundtrack, the video runs as long as the speech, from 1 second to 3 minutes, and a prompt can steer motion and expression. It offers 30 voices across 10 languages with delivery instructions for tone and pacing, and outputs from 480p up to 4K for course instructors, localized product walkthroughs, and personalized outreach.

API Options

Platform-level options for task execution and delivery.

taskType stringrequiredvalue: videoInference: Identifier for the type of task being performed.

taskUUID stringrequiredUUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType stringdefault: URL: Video output type.
Allowed values1 value

outputFormat stringdefault: MP4

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP4`: Widely supported video container (H.264), recommended for general use.
`WEBM`: Optimized for web delivery.
`MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Allowed values3 values

outputQuality integermin: 20max: 99default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL stringuri

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more1 resource

Webhooks
PLATFORM

deliveryMethod stringdefault: async

Determines how the API delivers task results.

Allowed values2 values

: Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more1 resource

Task Polling
PLATFORM

uploadEndpoint stringuri

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

safety object

Content safety checking configuration for video generation.

Properties2 properties

safety » checkContent checkContent boolean: Enable or disable content safety checking. Increases total generation time.

safety » mode mode stringdefault: fast

Safety checking mode for video generation.

Allowed values2 values

: Checks key frames.
: Checks all frames.

ttl integermin: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean: Include task cost in the response.

numberResults integermin: 1max: 4default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

routing object

Model router options. Only read when model is auto, and never sent to the model.

Properties3 properties

routing » preferences preferences object

Relative importance of each dimension when models are compared. Weights, not thresholds.

Properties3 properties

routing » preferences » quality quality integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » preferences » speed speed integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » preferences » cost cost integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » maxPrice maxPrice floatmin: 0: Upper bound on what this request may cost, in USD. A model whose cost cannot be bounded is not chosen.

routing » requirements requirements stringmax: 3000: Conditions the result has to meet, in plain words, such as a style or a feature. A model that cannot meet them is not chosen. Output size is set with width and height rather than described here.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » image image stringrequired1 limit: Image input (UUID, URL, Data URI, or Base64). Portrait used as the first frame. It sets the aspect ratio, and is cropped to the output canvas when its ratio is outside the supported range.

inputs » audio audio string2 limits: Audio input (UUID or URL). Speech the portrait speaks. The video matches its length.

Core Parameters

Primary parameters that define the task output.

model stringrequiredvalue: prunaai:p-video@2-pro-avatar

Send auto instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See Model Router.

Learn more3 resources

positivePrompt stringmin: 1

Text prompt describing elements to include in the generated output.

Learn more1 resource

Prompts
LEARN

resolution stringdefault: 768p: Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. 1080p, 2k and 4k upscale the 768p render. At 4k the audio can be at most 125 seconds.
Allowed values5 values

seed integermin: 0max: 2147483647: Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

speech object

Settings for speech generation.

Properties3 properties

speech » text text stringmin: 1max: 5000: Text to convert to speech.

speech » voice voice stringdefault: Zephyr (Female): Voice identifier to use for speech generation.
Allowed values30 values

speech » language language stringmin: 1default: English (US): Language code for speech generation.
Allowed values10 values

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » promptUpsampling promptUpsampling booleandefault: true: Automatically enhance the prompt for improved results.

settings » safetyFilter safetyFilter boolean: Content safety filtering.

settings » voicePrompt voicePrompt stringmin: 1default: Say the following.: Speaking style, tone, pacing, or emotion instructions for delivery.