Akool

Akool is a generative AI platform for video and imagery - talking avatars, talking photos, face swap, video translation with lip-sync, background change, image generation, and a real-time streaming (live) avatar product. The Akool OpenAPI exposes these tools as an HTTPS REST API under https://openapi.akool.com, authenticated with a Bearer token minted from a clientId / clientSecret pair (or a direct x-api-key). Generation is asynchronous - callers create a task, then poll by id or receive an encrypted webhook callback when the task completes. The Live Avatar product opens a real-time session whose media is carried over a third-party WebRTC transport (Agora, LiveKit, or TRTC).

6 APIs 0 Features
AI AvatarsVideo GenerationAI VideoFace SwapGenerative AITalking AvatarVideo TranslationLive Avatar

APIs

Akool Talking Avatar API

Generate an expressive, speaking avatar video from an Akool or user-supplied avatar plus text or an audio track. Create a task with POST /api/open/v3/talkingavatar/create using ...

Akool Talking Photo API

Turn a still portrait into a talking video by pairing a talking_photo_url with an audio_url. Create with POST /api/open/v3/content/video/createbytalkingphoto (optional prompt fo...

Akool Face Swap API

Swap a source face onto a target image or video, single-face or multi-face via a face_mapping array, with model_style and face_enhance options. Create with POST /api/open/v4/fac...

Akool Video Translation API

Translate a source video into one or more target languages with optional lip-sync, speaker detection, background-music removal, and caption handling. List supported languages wi...

Akool Image Generation API

Text-to-image and image-to-image generation on Flux-family models, with aspect-ratio, resolution (up to 4k), and batch (1-4) controls. Create with POST /api/open/v4/content/imag...

Akool Live Avatar (Streaming) API

Real-time, interactive streaming avatars. The REST control plane lists avatars (GET /api/open/v4/liveAvatar/avatar/list) and manages sessions (create, list, detail, close). Sess...

Collections

Akool OpenAPI

OPEN

Pricing Plans

Akool Plans Pricing

5 plans

PLANS

Rate Limits

Akool Rate Limits

4 limits

RATE LIMITS

FinOps

Akool Finops

FINOPS

Resources

🔗
AgenticAccess
AgenticAccess
🔑
Authentication
Authentication
👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
Website
Website
🔗
Documentation
Documentation
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
📰
Blog
Blog

Sources

Raw ↑ 
opencollection: 1.0.0
info:
  name: Akool OpenAPI
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Authentication
    type: folder
  items:
  - info:
      name: Get API token
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v3/getToken
      body:
        type: json
        data: '{"clientId":"","clientSecret":""}'
    docs: Exchange clientId and clientSecret for a Bearer token.
- info:
    name: Talking Avatar
    type: folder
  items:
  - info:
      name: Create talking avatar video
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v3/talkingavatar/create
      body:
        type: json
        data: '{"avatar_from":2,"avatar_id":"","voice_id":"","input_text":"Hello from Akool"}'
    docs: Generate a speaking avatar video from text or audio. Poll status by the returned _id.
- info:
    name: Talking Photo
    type: folder
  items:
  - info:
      name: Create talking photo video
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v3/content/video/createbytalkingphoto
      body:
        type: json
        data: '{"talking_photo_url":"","audio_url":"","resolution":"1080p"}'
    docs: Animate a still portrait with an audio track.
  - info:
      name: Poll video status
      type: http
    http:
      method: GET
      url: https://openapi.akool.com/api/open/v3/content/video/infobymodelid
      params:
      - name: video_model_id
        value: ''
        type: query
        description: The _id returned by a create request.
    docs: Poll a content video task by its model id.
- info:
    name: Face Swap
    type: folder
  items:
  - info:
      name: Face swap by image
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v4/faceswap/faceswapPlusByImage
      body:
        type: json
        data: '{"source_url":"","target_url":"","single_face_mode":true,"model_style":"realistic"}'
    docs: Swap a source face onto a target image or video.
  - info:
      name: Get face swap results by ids
      type: http
    http:
      method: GET
      url: https://openapi.akool.com/api/open/v3/faceswap/result/listbyids
      params:
      - name: _ids
        value: ''
        type: query
        description: Comma-separated result ids.
    docs: Retrieve face swap results by a comma-separated list of ids.
- info:
    name: Video Translation
    type: folder
  items:
  - info:
      name: List supported languages
      type: http
    http:
      method: GET
      url: https://openapi.akool.com/api/open/v3/language/list
    docs: List languages supported for video translation.
  - info:
      name: Create video translation
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v3/content/video/createbytranslate
      body:
        type: json
        data: '{"url":"","language":"Spanish,French","source_language":"DEFAULT","lipsync":true}'
    docs: Translate a video into one or more target languages with optional lip-sync.
- info:
    name: Image Generation
    type: folder
  items:
  - info:
      name: Generate image by source prompt
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v4/content/image/createBySourcePrompt
      body:
        type: json
        data: '{"prompt":"a cinematic portrait","scale":"1:1","resolution":"4k","batch_quantity":1}'
    docs: Text-to-image or image-to-image generation.
  - info:
      name: Poll image status
      type: http
    http:
      method: GET
      url: https://openapi.akool.com/api/open/v3/content/image/infobymodelid
      params:
      - name: image_model_id
        value: ''
        type: query
        description: The _id returned by a create request.
    docs: Poll an image generation task by its model id.
- info:
    name: Live Avatar
    type: folder
  items:
  - info:
      name: List streaming avatars
      type: http
    http:
      method: GET
      url: https://openapi.akool.com/api/open/v4/liveAvatar/avatar/list
      params:
      - name: page
        value: '1'
        type: query
      - name: size
        value: '20'
        type: query
    docs: List available streaming avatars.
  - info:
      name: Create live avatar session
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v4/liveAvatar/session/create
      body:
        type: json
        data: '{"avatar_id":"","stream_type":"agora","agora_channel":"","agora_token":"","agora_uid":0}'
    docs: Open a real-time streaming avatar session. Media rides a caller-selected WebRTC transport (agora, livekit, or trtc)
      - not an Akool WebSocket.
  - info:
      name: Close live avatar session
      type: http
    http:
      method: POST
      url: https://openapi.akool.com/api/open/v4/liveAvatar/session/close
      body:
        type: json
        data: '{"id":""}'
    docs: Close an open streaming avatar session by id.