Skip to content

Latest commit

 

History

History
114 lines (93 loc) · 3.87 KB

README.md

File metadata and controls

114 lines (93 loc) · 3.87 KB
Raw

🪄 API v2 is launching soon with major updates to the API and capabilites. Stay tuned!

API documentation

Your users can generate audio and video content with our AI-powered Fliki API. They can generate content in 75+ languages, 1000+ voices and 100+ dialects!

Version

Fliki API v1

Pricing

API is bundled with the premium plan.

API key

Samples

API endpoints

Language list

Get list of languages

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -X GET https://api.fliki.ai/v1/languages

Dialect list

Get list of dialects

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -X GET https://api.fliki.ai/v1/dialects

Returns list of dialects.

Voice list

Get list of voices (along with supported voice styles) by language (required) and dialect (required)

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -d '{"languageId": "<LANUGAGE ID>", "dialectId": "<DIALECT ID>"}' \
  -X POST https://api.fliki.ai/v1/voices

Returns list of voices.

Generate video / voiceover

Generate video or voiceover for given scenes

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -d '{"format": "video", "scenes": [{"content": "<CONTENT 1>", "voiceId": "<VOICE ID>"}, {"content": "<CONTENT 2>", "voiceId": "<VOICE ID>"}], "settings": {}, "backgroundMusicKeywords": "<KEYWORDS>"}' \
  -X POST https://api.fliki.ai/v1/generate

Returns ID which you can pass to Generate status to check status and receive download URL.

format = video | audio

settings =

{ aspectRatio: 'portrait' | 'square' | 'horizontal' }

backgroundMusicKeywords (optional) = eg: 'happy, lofi, beats'

Generate status

Check status for generate requests and download generated file

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -d '{"id": "<ID>"}' \
  -X POST https://api.fliki.ai/v1/generate/status

Returns status and download URL.

Generate text-to-speech

Generate audio for given content (plain text or SSML, required), voice (required) and voiceStyle (optional)

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -d '{"content": "<CONTENT>", "voiceId": "<VOICE ID>", "voiceStyleId": "<VOICE STYLE ID>"}' \
  -X POST https://api.fliki.ai/v1/generate/text-to-speech

Returns download URL.

Generate text-to-image

Generate image using AI for given content (plain text, required) and style (optional)

curl \
  -H "Authorization: Bearer <API KEY>" \
  -H "Content-Type: application/json" \
  -d '{"content": "<CONTENT>", "style": "<STYLE>"}' \
  -X POST https://api.fliki.ai/v1/generate/text-to-image

Returns download URL.

style = 3d-model | analog-film | anime | cinematic | comic-book | digital-art | enhance | fantasy-art | isometric | line-art | low-poly | modeling-compound | neon-punk | origami | photographic | pixel-art | tile-texture

Note

  • Input data field content across all applicable endpoint is limited to 1000 characters.
  • The file generated are hosted on Fliki's storage server and is deleted automatically after an hour. We expect you to copy it to your own storage server for long term availability.
  • The API service (v1) is in early access only. The endpoints and other workings of API is subjected to change without notice.

Contact

Share your feedback, feature requests and bug reports via email support@fliki.ai or via live chat available on fliki.ai.