Pruna AI P Video 2 Pro Text To Video API Documentation

Pruna AI P Video 2 Pro Text To Video API Documentation

Playground

Pruna P-Video-2-Pro Text-to-Video generates videos from text prompts at 480P / 768P output with generated audio, supporting prompt-driven video creation for creative clips, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Pruna P-Video-2 Pro Text-to-Video generates videos directly from text prompts with generated audio. Describe the scene, subject, motion, camera movement, and visual style, then choose duration, aspect ratio, resolution, generation mode, and prompt upsampling settings.

Why Choose This?

• Text-to-video generation
  Generate videos directly from natural-language prompts.

• Generated audio included
  Output video includes generated audio without requiring separate audio input.

• 480p and 768p output
  Use 480p for lower-cost generation or 768p for higher-resolution output.

• Cost, speed, and quality modes
  Choose mode=cost for lower-cost generation with the same output quality as speed, mode=speed for faster generation, or mode=quality for higher-quality generation. Default: speed.

• Prompt upsampling control
  Choose off, turbo, or max prompt expansion depending on how much prompt enhancement you need.

• Multiple aspect ratios
  Supports landscape, vertical, square, classic, and portrait video formats.

Parameters

How to Use

1. Write a prompt — Describe the scene, subject, action, camera movement, lighting, mood, and visual style.
2. Set duration — Choose a video length from 5 to 15 seconds.
3. Choose aspect ratio — Select the layout that matches your target format.
4. Choose resolution — Use 480p for lower-cost generation or 768p for higher-resolution output.
5. Choose generation mode — Select cost for lower-cost generation, speed for faster generation, or quality for higher-quality generation. Pricing depends on the selected mode and resolution.
6. Set prompt upsampling — Use off, turbo, or max depending on how much prompt expansion you want.
7. Set seed optional — Use a fixed seed for reproducible results, or omit it for random generation.
8. Submit — Generate the final video with audio.

Pricing

Pricing depends on the requested duration, resolution, and generation mode.

Example Costs

Billing Rules

• Billing uses the requested duration, not the measured output duration.
• Supported duration: 5–15 seconds.
• Generated audio is included.
• Prompt upsampling and seed selection do not add separate charges.
• Default settings: 768p, speed mode, 5 seconds — $0.175 per request.

Best Use Cases

• Text-to-video generation — Create videos directly from written scene descriptions.
• Cinematic concepts — Generate short scenes with camera movement, lighting, and visual style.
• Social video content — Create vertical, square, landscape, or portrait-format clips.
• Marketing and product videos — Generate short-form promotional clips from text prompts.
• Creative prototyping — Test motion, pacing, style, and audio direction before final production.
• Prompt iteration — Compare cost, speed, and quality generation modes and independently adjust prompt upsampling.

Pro Tips

• Write prompts that describe visible motion, not just the visual style.
• Include subject, action, environment, camera movement, lighting, mood, and scene progression.
• Keep the prompt focused on one main scene or action for stronger motion coherence.
• Use mode=cost to minimize price, mode=speed for faster iteration, or mode=quality when prioritizing output quality.
• Use prompt_upsampler=off when you want the model to follow your original prompt more directly.
• Use prompt_upsampler=max when the prompt is short and needs stronger expansion.
• Use 480p for lower-cost tests and 768p for higher-resolution output.
• Set a fixed seed when comparing prompt or parameter changes.

Notes

• prompt is required.
• duration supports values from 5 to 15 seconds.
• Generated audio is included in the output.
• Image conditioning and last-frame guidance are not exposed on this text-to-video product.

Related Models

• Pruna P-Video-2 Pro Text-to-Video — Generate Pro text-to-video outputs with generated audio.
• Pruna P-Video-2 Pro Image-to-Video — Generate Pro videos from an input image and motion prompt.
• Pruna P-Video-2 Text-to-Video — Generate videos directly from text prompts.
• Pruna P-Video-2 Image-to-Video — Generate videos from an input image and motion prompt.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "768p",
  "mode": "speed",
  "prompt_upsampler": "turbo"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-video-2-pro/text-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters