GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →

pruna-ai/

Pruna P-Video-2 Text-to-Video generates videos from text prompts with explicit controls for duration, resolution, draft mode, and audio output, making it suitable for creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
Input
Enable Safety Checker

Idle

$0.025per run·~40 / $1

Next:

ExamplesView all

A young woman boards the last city bus on a rainy night and sits beside the window, exhausted after a long day. At the next stop, a man enters carrying a wet bouquet of flowers and freezes when he sees her. She recognizes him too: he is the boy she once waited for years ago and never met. The bus pulls away as neither knows what to say at first. The camera starts outside the rain-streaked window, then slides into the warm bus interior, lingering on their hesitant expressions before moving into a gentle two-shot. Tender romantic drama, rainy city lights, quiet emotional tension.

n a crowded futuristic night market, a young man enters a hidden shop where memories are bought and sold as glowing glass capsules. He hands over one capsule and watches the shopkeeper play it inside a machine. The projected memory shows himself dancing with a woman he cannot remember. When he asks who she is, the shopkeeper looks frightened and says, “You already sold her.” The camera opens with vibrant neon market chaos, then becomes intimate and still inside the memory shop, pushing slowly toward the glowing capsule as the truth sinks in. Emotional sci-fi noir, moody neon color palette, cinematic storytelling.

Related Models

README

Pruna P-Video-2 Text-to-Video

Pruna P-Video-2 Text-to-Video generates videos directly from text prompts. Describe the scene, motion, camera movement, and visual style, then choose duration, resolution, and Draft or Full mode for fast previews or higher-quality output.

Why Choose This?

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

  • Explicit duration control
    Choose a requested duration from 1 to 20 seconds.

  • Draft and Full modes
    Use Draft mode for faster, lower-cost previews, or Full mode for higher-quality output.

  • 720p and 1080p output
    Generate at 720p for lower cost or 1080p for higher-resolution results.

  • Prompt upsampling
    Use prompt_upsampling to expand and refine the generation prompt.

  • Audio output option
    Keep save_audio enabled when audio should be saved in the generated result.

Parameters

ParameterRequiredDescription
promptYesNon-empty generation prompt describing the scene, motion, camera movement, subject action, and visual direction.
aspect_ratioNoOutput aspect ratio. Default: 16:9.
durationYesRequested video duration in seconds. Range: 1–20. No default is supplied.
resolutionNoOutput resolution: 720p or 1080p. Default: 720p.
draftNoEnable lower-quality Draft mode for faster, lower-cost previews. Default: false.
save_audioNoSave audio in the generated result when supported. Default: true.
prompt_upsamplingNoExpand and optimize the generation prompt. Default: true.
seedNoOptional non-negative integer seed for reproducible results. Omit for random generation.

How to Use

  1. Write a prompt — Describe the scene, subject, action, camera movement, lighting, mood, and visual style.
  2. Choose aspect ratio — Use the default 16:9 or select another supported layout.
  3. Set duration — Choose an explicit duration from 1 to 20 seconds.
  4. Choose resolution — Use 720p for lower-cost generation or 1080p for higher-resolution output.
  5. Choose Draft or Full mode — Enable draft for preview generation or leave it disabled for full output.
  6. Configure prompt upsampling optional — Keep prompt_upsampling enabled when you want the prompt refined automatically.
  7. Set seed optional — Use a fixed seed for reproducible results, or omit it for random generation.
  8. Submit — Generate the final text-to-video output.

Pricing

Pricing is based on the explicitly requested duration, selected resolution, and draft mode.

ResolutionFull / secondDraft / second
720p$0.025$0.015
1080p$0.05$0.03

Example Costs

Duration720p Full720p Draft1080p Full1080p Draft
5s$0.125$0.075$0.25$0.15
10s$0.25$0.15$0.50$0.30
20s$0.50$0.30$1.00$0.60

Billing uses the requested duration, not the measured duration of the generated output. aspect_ratio, save_audio, prompt_upsampling, and seed do not add separate charges.

Best Use Cases

  • Text-to-video generation — Create videos directly from written scene descriptions.
  • Prompt-based motion testing — Test different actions, camera movements, and visual styles.
  • Draft previews — Use Draft mode to compare ideas before running full-quality output.
  • Social video content — Generate short clips for ads, posts, reels, and creative previews.
  • Creative prototyping — Explore cinematic concepts, character scenes, or product visuals from text.
  • Marketing and product videos — Generate short-form promotional clips from text prompts.

Pro Tips

  • Write prompts that describe visible motion, not just the image style.
  • Include subject, action, camera movement, lighting, mood, and scene progression.
  • Use Draft mode for quick iteration before generating the final version.
  • Use 720p for lower-cost tests and 1080p for higher-resolution output.
  • Set a fixed seed when comparing prompt or parameter changes.
  • Keep prompts focused on one main scene or action for more stable motion.
  • This product does not support automatic duration, audio conditioning, or last-frame guidance.
  • Frame rate follows the upstream default.

Notes

  • prompt and duration are required.
  • duration must be explicitly set from 1 to 20 seconds.
  • Billing uses the requested duration.
  • Automatic duration, audio conditioning, and last-frame guidance are not available in this product.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

P Video 2 Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pruna-ai/p-video-2/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for P Video 2 Text To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "draft": false,
    "save_audio": true,
    "prompt_upsampling": true
}
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/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/pruna-ai/p-video-2/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "duration": 5,
        "aspect_ratio": "16:9",
        "resolution": "720p",
        "draft": false,
        "save_audio": true,
        "prompt_upsampling": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "draft": False,
    "save_audio": True,
    "prompt_upsampling": True
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/pruna-ai/p-video-2/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

P Video 2 Text To Video API — Frequently asked questions

What is the P Video 2 Text To Video API?

P Video 2 Text To Video is a Pruna Ai model for video generation, exposed as a REST API on WaveSpeedAI. Pruna P-Video-2 Text-to-Video generates videos from text prompts with explicit controls for duration, resolution, draft mode, and audio output, making it suitable for creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the P Video 2 Text To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-video-2-text-to-video.

How much does P Video 2 Text To Video cost per run?

P Video 2 Text To Video starts at $0.025 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does P Video 2 Text To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`, `draft`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-video-2-text-to-video.

How do I get started with the P Video 2 Text To Video API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use P Video 2 Text To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Pruna Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Pruna P-Video-2 Text-to-Video API on WaveSpeedAI