Synthesize a character's voice

POST

characters

{id}

tts

curl --request POST \
  --url https://api.alakazam.gg/v1/characters/{id}/tts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "token": "<string>",
  "style": 123
}
'

"<string>"

Authorizations

Authorization

string

header

required

The scoped runtime session JWT from POST /v1/sessions/token. The embed's browser presents it (Authorization: Bearer, or a token body field) to the runtime exchange routes. Not an API key.

Path Parameters

string<uuid>

required

Body

application/json

text

string

required

token

string

style

number

0–1 expressiveness.

Response

The synthesized audio.

The response is of type file.

Paint a show_image pictureThe picture a character is "showing you" (the show_image action). With a prompt it generates one (metered 'image'); with NO prompt — or if generation fails / the quota is hit — it returns the character's BASE image so a card never comes up empty.

⌘I

Synthesize a character's voice

curl --request POST \
  --url https://api.alakazam.gg/v1/characters/{id}/tts \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "token": "<string>",
  "style": 123
}
'

"<string>"