Create Narrated Slideshow

Creates a new video generation task from property images. The video is generated asynchronously - you’ll receive a task ID to poll for status or configure a webhook to be notified when complete.

Request Body

images

string[]

required

Array of image URLs for the slideshow. Must contain 6 to 15 images.Images should be:

Publicly accessible URLs
JPEG, PNG, or WebP format
Minimum resolution: 720p recommended
All URLs must be unique (no duplicates allowed)

For the best visual result, upload images that already match your target format. When orientation is set to portrait, the pipeline can expand landscape photos to fit a 9:16 output when needed.

orientation

string

Optional output orientation for the final video.

Value	Description
`landscape`	Generate a horizontal 16:9 video
`portrait`	Generate a vertical 9:16 video

If omitted, VibePeak auto-detects the orientation from the first image and defaults to landscape if detection is not possible.

Choosing portrait is useful when you want social-first vertical output from a mixed or landscape-heavy photo set.

voice

object

required

Voice configuration for the AI-generated narration.

Show Voice properties

voice_id

string

required

Voice ID to use for narration. You can find available voices using the List Voices endpoint.

language

string

required

ISO 639-1 language code for TTS pronunciation (e.g., en, es, de, fr, pt).This helps produce more accurate pronunciation for the target language.

Use the same language code as the script content for best results.

script

string

required

Narration script for text-to-speech.The script length must be proportional to the number of images to ensure proper narration pacing (~3 seconds per image):

Images	Min Characters	Max Characters
6	240	300
10	400	500
15	600	750

Formula: min = images × 40, max = images × 50

No numbers or special symbols allowed. The script must contain only letters, spaces, and basic punctuation (. , ! ? ; : ' " -). Numbers must be written as words (e.g., “three” instead of “3”) and symbols like @, #, $, %, &, (, ) are not permitted. This ensures optimal text-to-speech audio quality.

Scripts that are too short or too long for the number of images will be rejected with SCRIPT_TOO_SHORT or SCRIPT_TOO_LONG error codes.

orchestration_mode

string

default:"artistic"

Video orchestration mode that controls scene pacing and transitions.

Value	Description
`standard`	Standard mode with scenes of 3-7 seconds
`artistic`	Cinematic mode with 2-3 second scenes and visual weight hierarchy (default)
`sequential`	Images appear in order without AI reordering. Scene duration is auto-calculated.

webhook_url

string

URL to receive webhook notification when the task completes.Must be a valid HTTPS URL. See Webhooks for details.

Webhook URLs must use HTTPS and cannot point to private/internal networks (SSRF protection).

avatar_id

string

Optional UUID of an avatar to include in the video.Must be a valid UUID v4 format (e.g., 123e4567-e89b-12d3-a456-426614174000).

background_music

boolean

default:"false"

Enable AI-generated background music for the video.When true, generates calm ambient music that matches the video duration. The music is automatically generated with a real estate style (soft piano, elegant, minimal) and mixed at 20% volume to complement the narration.

Background music generation adds a few seconds to the processing time. If music generation fails, the video will still be created without background music.

subtitle

object

Subtitle configuration for word-level animated overlays. Use subtitle_style_preset for quick setup or styles for granular control. Providing both will result in a validation error.

Show Subtitle Config properties

subtitle_style_preset

string

Name of a predefined style to apply. Options: classic, cinematic, gradient, handwritten, hustle, karaoke_highlight_no_box, karaoke_red_box_phrase, karaoke_word_box_clip, minimal, neon, one_word_red_box, phrase_yellow, retro, tiktok_default, youtube_caption.

styles

object

Granular styling properties for subtitle rendering.

Show Styles properties

alignment

integer

default:"2"

SSA alignment: 1-9 (e.g., 2 for bottom-center).

backColor

string

default:"#000000"

Background color in hex format (e.g., #000000).

backOpacity

integer

default:"100"

Transparency of background box: 0-255.

behavior

string

default:"phrase_blocks"

Subtitle reveal behavior. Options: phrase_blocks, one_word, karaoke_highlight, karaoke_box_word.

borderStyle

integer

default:"1"

Border style: 1 (Outline) or 3 (Box).

fontFamily

string

default:"Arial"

System font name.

fontSize

integer

default:"28"

Font size in pixels (14-96).

marginL

integer

default:"40"

Left margin in pixels (0-500).

marginR

integer

default:"40"

Right margin in pixels (0-500).

marginV

integer

default:"200"

Vertical/Bottom margin in pixels (0-500).

maxGapSeconds

number

default:"0.3"

Max silence (sec) between words before phrase break (0.01-2).

maxWordsPerLine

integer

default:"6"

Automatic line wrapping constraint (1-12).

outline

integer

default:"2"

Thickness of text stroke (0-10).

outlineColor

string

default:"#000000"

Color of text stroke in hex format.

primaryColor

string

default:"#FFFFFF"

Default text color in hex format.

secondaryColor

string

default:"#FFFFFF"

Alt color for highlights/karaoke in hex format.

shadow

integer

default:"0"

Thickness of text drop shadow (0-10).

elements_config

object

Configuration for visual elements and branding overlays. If not provided, elements are disabled by default.

Show Elements Config properties

enabled

boolean

default:"false"

Global toggle for the elements overlay feature.

watermark

object

Watermark (logo) branding configuration.

Show Watermark properties

url

string

required

URL of the uploaded watermark image. Must be a valid public URL.

position

string

default:"bottom-right"

Anchor point for the watermark placement. Options: top-left, top-center, top-right, center-left, center, center-right, bottom-left, bottom-center, bottom-right.

size

number

default:"20"

Relative scale percentage of the watermark (0-100).

opacity

number

default:"100"

Transparency level (0 for transparent, 100 for opaque).

text

object

Text overlay configuration for static labels or call-to-actions.

Show Text properties

content

string

required

Text content to be rendered on the video (max 20 characters).

color

string

default:"#FFFFFF"

Hex color code for the text (e.g., #FFFFFF).

font

string

default:"Inter"

Font family for the text overlay. Options: Alegreya, DM Mono, Inter, Libre Bodoni, Quicksand, Roboto, Raleway, Noto Sans, Zilla Slab.

opacity

number

default:"100"

Transparency level of the text (0-100).

size

number

default:"20"

Font size scale relative to video height (1-100).

position

string

default:"center"

Anchor point for the text placement. Same options as watermark position.

Scene Duration Overrides

For fine-tuned control over video pacing, you can override the default scene durations.

min_scene_duration_seconds

number

Minimum duration for each scene in seconds. Range: 1-30.

max_scene_duration_seconds

number

Maximum duration for each scene in seconds. Range: 1-30.

Artistic Mode Duration Overrides

When using orchestration_mode: "artistic", you can separately control hero and secondary scene durations.

hero_min_duration_seconds

number

Minimum duration for hero (primary) scenes in seconds. Range: 1-30.

hero_max_duration_seconds

number

Maximum duration for hero (primary) scenes in seconds. Range: 1-30.

secondary_min_duration_seconds

number

Minimum duration for secondary scenes in seconds. Range: 1-30.

secondary_max_duration_seconds

number

Maximum duration for secondary scenes in seconds. Range: 1-30.

Test Mode

test_scenario

string

default:"success"

Sandbox-only scenario selector. Honored only for test-mode (vpk_test_) keys and silently ignored for live keys, so it is safe to leave in shared request-building code.

Value	Outcome
`success`	Synthetic task completes with a watermarked sample video
`fail`	Synthetic task fails with a sanitized, public-safe error
`slow`	Like `success`, but completes after a noticeably longer delay

Test mode never spends credits or runs the real pipeline. See Test Mode for the full sandbox model.

Response

task_id

string

required

Unique identifier for the task. Use this to check status.

status

string

required

Initial task status. Always queued for new tasks.

queue_position

integer

Position in the processing queue.

estimated_completion

string

Estimated completion time (ISO 8601 format).

created_at

string

required

Task creation timestamp (ISO 8601 format).

livemode

boolean

required

true for live (vpk_live_) requests; false for test-mode (vpk_test_) requests. Use this to tell a real task from a sandbox one. See Test Mode.

curl -X POST https://api.vibepeak.ai/v1/real-estate/narrated-slideshow \
  -H "Authorization: Bearer vpk_live_xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "images": [
      "https://example.com/property/living-room.jpg",
      "https://example.com/property/kitchen.jpg",
      "https://example.com/property/bedroom.jpg",
      "https://example.com/property/bathroom.jpg",
      "https://example.com/property/backyard.jpg",
      "https://example.com/property/exterior.jpg"
    ],
    "voice": {
      "voice_id": "EXAVITQu4vr4xnSDxMaL",
      "language": "en"
    },
    "orientation": "portrait",
    "script": "Welcome to this stunning 3-bedroom home in the heart of the city. The open-concept living area floods with natural light...",
    "orchestration_mode": "standard",
    "webhook_url": "https://yourserver.com/webhooks/vibepeak",
    "background_music": true,
    "subtitle": {
      "subtitle_style_preset": "classic"
    },
    "elements_config": {
      "enabled": true,
      "watermark": {
        "url": "https://example.com/logo.png",
        "position": "bottom-right",
        "size": 20,
        "opacity": 100
      },
      "text": {
        "content": "Powered by Vibepeak",
        "color": "#FFFFFF",
        "font": "Inter",
        "size": 20,
        "position": "center"
      }
    }
  }'

{
  "task_id": "task_abc123xyz",
  "status": "queued",
  "queue_position": 3,
  "estimated_completion": "2026-01-04T12:30:00Z",
  "created_at": "2026-01-04T12:00:00Z",
  "livemode": true
}

Error Codes

Code	Status	Description
`VALIDATION_ERROR`	400	Invalid request parameters
`INVALID_IMAGE_URL`	400	One or more image URLs are inaccessible or invalid
`SCRIPT_TOO_SHORT`	400	Script is too short for the number of images (min 40 chars/image)
`SCRIPT_TOO_LONG`	400	Script is too long for the number of images (max 50 chars/image)
`SCRIPT_INVALID_CHARACTERS`	400	Script contains numbers or special symbols not supported by TTS
`INVALID_API_KEY`	401	Invalid or missing API key
`PLAN_REQUIRED`	403	Plan doesn’t include API access
`CONCURRENCY_LIMIT_EXCEEDED`	429	Concurrent task limit reached
`SERVICE_UNAVAILABLE`	503	Video generation service temporarily unavailable
`SERVICE_TIMEOUT`	504	Service request timed out

See Error Handling for more details.

Next Steps

After creating a task:

Poll for status: Use Get Task to check progress
Wait for webhook: If configured, receive notification when complete
Download video: Access the video URL from the completed task result

Overview

Avatars

Voices

Videos

Create Narrated Slideshow

Request Body

Scene Duration Overrides

Artistic Mode Duration Overrides

Test Mode

Response

Error Codes

Next Steps

Overview

Avatars

Voices

Videos

Documentation Index

​Request Body

​Scene Duration Overrides

​Artistic Mode Duration Overrides

​Test Mode

​Response

​Error Codes

​Next Steps

Request Body

Scene Duration Overrides

Artistic Mode Duration Overrides

Test Mode

Response

Error Codes

Next Steps