Generate Speech

Generate speech task

Price: 2.22$

Generate Speech Task

curl --location 'https://api.unifically.com/higgsfield/speech' \
--header 'Authorization: Bearer APIKEY' \
--header 'Content-Type: application/json' \
--data '{
  "avatar_preset_id": "7f1kmlzvtCNncSqUYMTbU",
  "prompt": "good",
  "width": 705,
  "height": 829,
  "image": [
    ""
  ],
  "audio": ""
}'

Fields

type

Details

avatar_preset_id

string

Get avatar from avatar-presets api

prompt

string

Prompt

image

string[]

url base64 Autobiography avatar, supports url base64

audio

string

url (wav/mp3) 13s speak The duration of the voice URL file (wav/mp3) cannot exceed 13 seconds. Choose between "speak" and "voice".

speak

object

Choose between text-to-speech and audio

speak.voice_id

string

Get voices from voices API

speak.sound_id

string

Get Sound ids from sound API

speak.text

string

Text to speech

Get Template Endpoints

curl --location 'https://api.unifically.com/higgsfield/tpl/sounds' \
--header 'Authorization: Bearer APIKEY' \
--header 'Content-Type: application/json'

curl --location 'https://api.unifically.com/higgsfield/tpl/avatar-presets' \
--header 'Authorization: Bearer APIKEY' \
--header 'Content-Type: application/json'

curl --location 'https://api.unifically.com/higgsfield/tpl/voices' \
--header 'Authorization: Bearer APIKEY' \
--header 'Content-Type: application/json'

curl --location 'https://api.unifically.com/higgsfield/tpl/motions' \
--header 'Authorization: Bearer APIKEY' \
--header 'Content-Type: application/json'

Last updated