Skip to main content
Upload speech, pick an avatar, and get back an MP4 of the avatar saying it, lip-synced to the audio. These endpoints let you create talking-avatar videos from your own systems, and list, download and delete them.

Authentication

Send your API key in the X-API-KEY header on every request, to the base URL https://api-eg.olimi.ai. See API Authentication. You only ever see the videos that belong to the company your API key is issued to.

How it works

Video generation runs in the background:
  1. Pick an avatar: List avatars and take a model_config_id.
  2. Create: Create a video with your audio file and that ID. It returns straight away with status: "queued".
  3. Poll: call Get video progress every few seconds until status is completed, failed or cancelled.
  4. Download: once it’s completed, get the file from Download a video, or from videoAttachment.url in Get a video.
To make the audio in the first place, you can use Text to Speech.

Video fields

Responses also carry internal fields. They may change without notice, so rely only on the fields listed on this page.

Status values

Errors

Always branch on statusCode first. Errors from this API come in three shapes:
  • 401 and 404: { "statusCode", "errorCode", "message" }, for example errorCode: "stv_job_not_found".
  • 400: { "statusCode", "message", "error" }. There’s no errorCode; the message says what went wrong.
  • Validation (422): message is a list of what went wrong.
An unknown configId doesn’t return an error: the video is created, then ends with status: "failed" and an errorMessage saying the configuration wasn’t found. Take configId from List avatars. The message text is for humans and may change.