Skip to main content
POST
/
api
/
v1
/
sessions
Create Session
curl --request POST \
  --url https://api.avaturn.live/api/v1/sessions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "avatar_id": "jane_20240829",
  "conversation_engine": {
    "type": "text-echo",
    "tts": {
      "engine": "elevenlabs",
      "voice_id": "<voice-id-here>"
    }
  },
  "background": "default",
  "model": "delta"
}'
{
  "session_id": "<string>",
  "token": "<string>"
}

Authorizations

​
Authorization
string
header
required

Project developer API token

Body

application/json
​
avatar_id
string
default:jane_20240829

Avatar ID

​
conversation_engine
object | null

Configures how avatar listens and responds Text-based echo conversation engine.

Allows controlling what avatar says with text. The text is converted into audio using TTS engine. Multiple TTS engines are supported.

  • TextEchoEngineConfig
  • OpenAIRealtimeAPICEConfig
​
background
enum<string>
default:default

Background type for the avatar. 'transparent' removes the background, 'default' uses the avatar's default background

Available options:
transparent,
default
​
model
enum<string>
default:delta
Available options:
delta,
golf

Response

Successful Response

​
session_id
string
required

Session ID

​
token
string
required

Session token for Web SDK