Skip to main content
POST
/
api
/
lipsyncs
/
preview
/
cURL
curl --request POST \
  --url https://api.creatify.ai/api/lipsyncs/preview/ \
  --header 'Content-Type: application/json' \
  --header 'X-API-ID: <api-key>' \
  --header 'X-API-KEY: <api-key>' \
  --data '{
  "name": "<string>",
  "text": "<string>",
  "audio": "<string>",
  "creator": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "model_version": "standard",
  "aspect_ratio": "16x9",
  "green_screen": true,
  "transparent_background": true,
  "webhook_url": "<string>",
  "accent": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "no_caption": true,
  "no_music": true,
  "caption_style": "normal-black",
  "caption_offset_x": "<string>",
  "caption_offset_y": "<string>"
}'
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "<string>",
  "text": "<string>",
  "creator": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "model_version": "standard",
  "output": "<string>",
  "video_thumbnail": "<string>",
  "aspect_ratio": "16x9",
  "green_screen": true,
  "transparent_background": true,
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "credits_used": 123,
  "duration": 123,
  "progress": "<string>",
  "failed_reason": "<string>",
  "media_job": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "<string>",
  "is_hidden": true,
  "audio_url": "<string>",
  "webhook_url": "<string>",
  "accent": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "preview": "<string>",
  "editor_url": "<string>",
  "preview_audio": "<string>",
  "no_caption": true,
  "no_music": true,
  "caption_style": "normal-black",
  "caption_offset_x": "<string>",
  "caption_offset_y": "<string>"
}

​
About preview Field in the Response

The preview field provides a link to preview the video. This link allows you to preview the video before rendering it, you can put it in an iframe to show the video in your application. Example: The preview field in the response will look like this: 
"https://app.creatify.ai/preview?layout=videos/20241024/f0c1e1f1-be05-48e0-91d8-3d26ed633d5b.json"

Authorizations

​
X-API-ID
string
header
required

API ID, from your settings page.

​
X-API-KEY
string
header
required

API Key, from your settings page.

Body

​
aspect_ratio
enum<string>
required

The aspect ratio of the video

  • 16x9 - Ratio 16 9
  • 1x1 - Ratio 1 1
  • 9x16 - Ratio 9 16
Available options:
16x9,
1x1,
9x16
​
name
string | null

The name of the lipsync request.

Maximum length: 255
​
text
string | null

The text to be used for voiceover

Maximum length: 8000
​
audio
string<uri> | null

Use your own audio file url for lipsync instead of the voiceover generated by us from text input. Either audio or text is required. If both are provided, audio will be used

​
creator
string<uuid> | null

The creator id associated with the lipsync request, you can get the list of creators from /api/personas endpoint.

​
model_version
enum<string>

Model version for the avatar, 'standard', 'aurora_v1' or 'aurora_v1_fast'. Default is 'standard'. Standard model costs 5 credits per 30 seconds video, Aurora_v1 model costs 20 credits per 15 seconds video, and Aurora_v1_fast renders faster with lower quality for 10 credits per 15 seconds video.

  • standard - Standard
  • aurora_v1 - Aurora v1
  • aurora_v1_fast - Aurora v1 Fast
Available options:
standard,
aurora_v1,
aurora_v1_fast
​
green_screen
boolean

When true, the output video will be in .mp4 format with black background and subtitles will not be rendered on the video. Default is false.

​
transparent_background
boolean

When true, the output video will be in .webm format with alpha channel (transparency support). Default is false.

​
webhook_url
string<uri> | null

The webhook URL to be called upon completion of the lipsync request

Maximum length: 200
​
accent
string<uuid> | null

The avatar id to be used for lipsync, you can get the list of accents from /api/voices endpoint.

​
no_caption
boolean

Whether to include captions in the output video. Default is true, video without caption.

​
no_music
boolean

Whether to include background music in the output video. Default is true, video without music.

​
caption_style
enum<string>

The style of the captions

  • normal-black - NORMAL_BLACK
  • normal-white - NORMAL_WHITE
  • normal-red - NORMAL_RED
  • normal-blue - NORMAL_BLUE
  • neo - NEO
  • brick - BRICK
  • frenzy - FRENZY
  • verana - VERANA
  • mustard - MUSTARD
  • glow - GLOW
  • mint - MINT
  • coolers - COOLERS
  • bilo - BILO
  • toons - TOONS
  • deep-blue - DEEP_BLUE
  • mystique - MYSTIQUE
  • caution - CAUTION
  • duality - DUALITY
  • comic-shadow - COMIC_SHADOW
  • clean-bold - CLEAN_BOLD
  • soft-pill - SOFT_PILL
  • underline-bold - UNDERLINE_BOLD
  • classic-duo - CLASSIC_DUO
  • hand-script - HAND_SCRIPT
  • button-glow - BUTTON_GLOW
  • emboss-outline - EMBOSS_OUTLINE
  • standard-bold - STANDARD_BOLD
  • outlined-text - OUTLINED_TEXT
  • quiet-serif - QUIET_SERIF
  • editorial-clean - EDITORIAL_CLEAN
  • shout-block - SHOUT_BLOCK
  • word-flash - WORD_FLASH
  • promo-punch - PROMO_PUNCH
  • light-word - LIGHT_WORD
  • tagline-bold - TAGLINE_BOLD
  • glow-speak - GLOW_SPEAK
  • black-block - BLACK_BLOCK
Available options:
normal-black,
normal-white,
normal-red,
normal-blue,
neo,
brick,
frenzy,
verana,
mustard,
glow,
mint,
coolers,
bilo,
toons,
deep-blue,
mystique,
caution,
duality,
comic-shadow,
clean-bold,
soft-pill,
underline-bold,
classic-duo,
hand-script,
button-glow,
emboss-outline,
standard-bold,
outlined-text,
quiet-serif,
editorial-clean,
shout-block,
word-flash,
promo-punch,
light-word,
tagline-bold,
glow-speak,
black-block
​
caption_offset_x
string<decimal>

Caption offset x is horizontaly relative to the center of the canvas in percentage, range from -0.5 to 0.5, default to 0

​
caption_offset_y
string<decimal>

Caption offset y is vertically relative to the center of the canvas in percentage, range from -0.5 to 0.5, default to -0.4, which is 40% below center

Response

200 - application/json
​
id
string<uuid>
required
​
output
string | null
required

Output video

​
video_thumbnail
string<uri>
required

Generated Video Thumbnail URL

​
aspect_ratio
enum<string>
required

The aspect ratio of the video

  • 16x9 - Ratio 16 9
  • 1x1 - Ratio 1 1
  • 9x16 - Ratio 9 16
Available options:
16x9,
1x1,
9x16
​
created_at
string<date-time>
required
​
updated_at
string<date-time>
required
​
credits_used
integer
required

Credits used in this API call

​
duration
integer
required

Duration of the video in seconds

​
progress
string
required
​
failed_reason
string | null
required

The reason for failure, if the lipsync request failed

​
media_job
string<uuid> | null
required

The media job associated with the lipsync request.

​
status
string
required

Status of the lipsync request

​
is_hidden
boolean
required

Is the video hidden in the website projects page

​
audio_url
string | null
required
​
preview
string | null
required

Preview video

​
editor_url
string | null
required

Editor URL for the video. Expires in 24 hours. Available only if your API account has API editor access enabled.

​
preview_audio
string | null
required

Preview audio

​
name
string | null

The name of the lipsync request.

Maximum length: 255
​
text
string | null

The text to be used for voiceover

Maximum length: 8000
​
creator
string<uuid> | null

The creator id associated with the lipsync request, you can get the list of creators from /api/personas endpoint.

​
model_version
enum<string>

Model version for the avatar, 'standard', 'aurora_v1' or 'aurora_v1_fast'. Default is 'standard'. Standard model costs 5 credits per 30 seconds video, Aurora_v1 model costs 20 credits per 15 seconds video, and Aurora_v1_fast renders faster with lower quality for 10 credits per 15 seconds video.

  • standard - Standard
  • aurora_v1 - Aurora v1
  • aurora_v1_fast - Aurora v1 Fast
Available options:
standard,
aurora_v1,
aurora_v1_fast
​
green_screen
boolean

When true, the output video will be in .mp4 format with black background and subtitles will not be rendered on the video. Default is false.

​
transparent_background
boolean

When true, the output video will be in .webm format with alpha channel (transparency support). Default is false.

​
webhook_url
string<uri> | null

The webhook URL to be called upon completion of the lipsync request

Maximum length: 200
​
accent
string<uuid> | null

The avatar id to be used for lipsync, you can get the list of accents from /api/voices endpoint.

​
no_caption
boolean

Whether to include captions in the output video. Default is true, video without caption.

​
no_music
boolean

Whether to include background music in the output video. Default is true, video without music.

​
caption_style
enum<string>

The style of the captions

  • normal-black - NORMAL_BLACK
  • normal-white - NORMAL_WHITE
  • normal-red - NORMAL_RED
  • normal-blue - NORMAL_BLUE
  • neo - NEO
  • brick - BRICK
  • frenzy - FRENZY
  • verana - VERANA
  • mustard - MUSTARD
  • glow - GLOW
  • mint - MINT
  • coolers - COOLERS
  • bilo - BILO
  • toons - TOONS
  • deep-blue - DEEP_BLUE
  • mystique - MYSTIQUE
  • caution - CAUTION
  • duality - DUALITY
  • comic-shadow - COMIC_SHADOW
  • clean-bold - CLEAN_BOLD
  • soft-pill - SOFT_PILL
  • underline-bold - UNDERLINE_BOLD
  • classic-duo - CLASSIC_DUO
  • hand-script - HAND_SCRIPT
  • button-glow - BUTTON_GLOW
  • emboss-outline - EMBOSS_OUTLINE
  • standard-bold - STANDARD_BOLD
  • outlined-text - OUTLINED_TEXT
  • quiet-serif - QUIET_SERIF
  • editorial-clean - EDITORIAL_CLEAN
  • shout-block - SHOUT_BLOCK
  • word-flash - WORD_FLASH
  • promo-punch - PROMO_PUNCH
  • light-word - LIGHT_WORD
  • tagline-bold - TAGLINE_BOLD
  • glow-speak - GLOW_SPEAK
  • black-block - BLACK_BLOCK
Available options:
normal-black,
normal-white,
normal-red,
normal-blue,
neo,
brick,
frenzy,
verana,
mustard,
glow,
mint,
coolers,
bilo,
toons,
deep-blue,
mystique,
caution,
duality,
comic-shadow,
clean-bold,
soft-pill,
underline-bold,
classic-duo,
hand-script,
button-glow,
emboss-outline,
standard-bold,
outlined-text,
quiet-serif,
editorial-clean,
shout-block,
word-flash,
promo-punch,
light-word,
tagline-bold,
glow-speak,
black-block
​
caption_offset_x
string<decimal>

Caption offset x is horizontaly relative to the center of the canvas in percentage, range from -0.5 to 0.5, default to 0

​
caption_offset_y
string<decimal>

Caption offset y is vertically relative to the center of the canvas in percentage, range from -0.5 to 0.5, default to -0.4, which is 40% below center