/speech

Send up to 3,000 characters and synchronously receive an MP3 and JSON timestamp URLs.

🤖

Processing Details

  • On average, 850 characters result in 1 minute of audio. In other words, 3,000 characters will result in approximately 3.5 minutes of audio.
  • On average, it takes 1 second per 700 characters. In other words, 3,000 characters will take approximately 4 seconds.
Body Params
string
required
Defaults to This is a test

This is the text to be synthesized to audio. Up to 3,000 characters.

string
required
Defaults to Scarlett

Scarlett, Dan, Liv, Will, Amy

string
Defaults to 192k

320k, 256k, 192k, ...

string
Defaults to 0

-1.0 to 1.0

string
Defaults to 1

0.5 to 1.5

string
Defaults to sentence

word or sentence

Response

Language
Credentials
Header
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json