Start speaker detection for a project

POST

/api/v1/audiobook/projects/{project_id}/assign-speakers

Path Parameters

project_id*Project Id

application/json

detect_emotions?Detect Emotions

Also pick a delivery emotion for each line

Defaultfalse

mode?Mode

'speakers' to attribute dialogue, 'emotions' to only mark narration emotion, 'both' to attribute then mark emotion in one run

Default"speakers"

Successful Response

response?unknownapplication/json

Example Request

curl -X POST 'http://127.0.0.1:8100/api/v1/audiobook/projects/string/assign-speakers' \
  -H 'Content-Type: application/json' \
  -d '{}'

Example Request

curl -X POST 'http://127.0.0.1:8100/api/v1/audiobook/projects/string/assign-speakers' \  -H 'Content-Type: application/json' \  -d '{}'

Example ResponseSchema

null

null

Estimate tokens and cost for speaker detection GET

Poll speaker detection progress GET