API Reference

Generate Speech Synchronously

Synthesize speech synchronously.

This endpoint returns binary 16-bit wav data with a sample rate of 22050 Hz.

Voice can be specified by providing either voice + model_type, or voicemodel_uuid.

Pace, duration, and pitch are only supported for voices that support these controls (a very small subset of voices).

You can check if a given voice supports controls by querying /voice-data or /voices/<voicemodel-uuid>/detail and looking at the controls boolean in the reponse.

POST

speak-synchronous

Authorization

Header

Body

curl --request POST \
  --url https://api.uberduck.ai/speak-synchronous \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "duration": [
    123
  ],
  "model_type": "<string>",
  "pace": 123,
  "pitch": [
    123
  ],
  "speech": "<string>",
  "voice": "<string>",
  "voicemodel_uuid": "<string>"
}'

This response has no body data.

Authorizations

Authorization

string

headerrequired

The access token received from the authorization server in the OAuth 2.0 flow.

Headers

uberduck-id

string

default: anonymous

Body

application/json

duration

number[]

model_type

string

pace

number

default: 1

pitch

number[]

speech

string

required

voice

string

default: lj

voicemodel_uuid

string

Get text-to-speech request status.Add Reference Audio

curl --request POST \
  --url https://api.uberduck.ai/speak-synchronous \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "duration": [
    123
  ],
  "model_type": "<string>",
  "pace": 123,
  "pitch": [
    123
  ],
  "speech": "<string>",
  "voice": "<string>",
  "voicemodel_uuid": "<string>"
}'

This response has no body data.