Short Video Generator
Playground
Try it on WaveSpeedAI!WaveSpeed Short Video Generator creates professional short-form videos from text prompts and optional reference images with native audio, smooth motion, and versatile aspect ratios. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Features
Short Video Generator produces professional short-form videos with native audio from text prompts and optional reference images. A versatile all-purpose model for creating polished clips across any format — landscape, vertical, or classic — with cinematic motion, realistic physics, and expressive character performance.
Why Choose This?
-
All-Purpose Short Video One model for every short-form need: ads, social posts, product demos, explainers, teasers, and more. No specialized pipeline required.
-
Native Audio Every video includes synchronized sound — ambient effects, background music, and dialogue with accurate lip-sync. Ready to publish without audio post-production.
-
Cinematic Motion Smooth, natural movement with professional camera work — tracking shots, dolly moves, rack focus, and handheld feel that elevate short-form content to broadcast quality.
-
Real-World Physics Objects interact naturally with proper weight, momentum, and collision. Fluid dynamics and realistic inertia make every scene believable.
-
Reference Image Support Upload up to 4 images to guide character appearance, product details, brand aesthetics, or scene composition for consistent results.
-
Every Aspect Ratio 16:9 for YouTube and web, 9:16 for TikTok and Reels, 4:3 and 3:4 for classic and editorial formats.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the scene, action, and mood for the video |
| images | No | Up to 4 reference images for style, character, or brand guide |
| aspect_ratio | No | 16:9 (default), 9:16, 4:3, or 3:4 |
| duration | No | 5 (default), 10, or 15 seconds |
How to Use
- Write your prompt — describe the scene with detail: environment, characters, action, lighting, and mood.
- Add reference images (optional) — upload product photos, character headshots, or style references.
- Select aspect ratio — pick the format for your target platform or use case.
- Set duration — 5s for bumpers and hooks, 10s for standard clips, 15s for mini-narratives.
- Generate — submit and receive a polished video with synchronized audio.
Pricing
| Duration | Cost |
|---|---|
| 5 s | $0.80 |
| 10 s | $1.60 |
| 15 s | $2.40 |
Billing Rules
- Rate: $0.80 per 5 seconds
- All aspect ratios are the same price
- Reference images do not affect pricing
Best Use Cases
- Marketing & Ads — Generate high-converting video ads with product reference images for brand consistency.
- Social Media — Produce platform-ready content for any social channel in the right aspect ratio.
- Product Demos — Showcase features and benefits with professional motion and lighting.
- Explainer Clips — Turn concepts into visual demonstrations with clear, engaging motion.
- Event Teasers — Create anticipation with dramatic, cinematic short clips.
- E-Commerce — Generate lifestyle product videos at scale from product photos.
Prompt Tips
- Be descriptive about the scene: Include environment, lighting, time of day, and atmosphere.
- Specify camera movement: “slow pan across the table”, “tracking shot following the subject”, “static close-up” all work well.
- Describe the mood: “energetic and upbeat”, “calm and serene”, “dramatic and tense” guide the overall feel.
- Use reference images strategically: Product shots maintain brand identity; character photos ensure face consistency.
- Match duration to content: 5s for punchy hooks, 10s for standard content, 15s for story-driven clips.
Notes
- Prompt is the only required field. Reference images are optional but improve consistency.
- Native audio is generated automatically with every video.
- Default aspect ratio is 16:9 (landscape).
- Duration options: 5, 10, or 15 seconds.
Related Models
- Cinematic Video Generator — Hollywood-grade cinematic video generation.
- TikTok Video Generator — Viral video generation for social platforms.
- Wan 2.6 Text-to-Video — Multi-resolution text-to-video.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"aspect_ratio": "16:9",
"duration": 5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/short-video-generator" \
-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 "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Describe the scene, action, camera movement, and mood for the video. | |
| images | array<string> | No | - | 0 ~ 4 items | Optional reference images (up to 4) to guide the visual style, characters, or scene composition. |
| aspect_ratio | string | No | 16:9 | 16:9, 9:16, 4:3, 3:4 | The aspect ratio of the generated video. |
| duration | integer | No | 5 | 5, 10, 15 | The duration of the generated video in seconds. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |