API Reference
These docs are for v1.0. Click to read the latest docs for v2.0.

Create a text-to-speech resource.

post
https://v2.api.audio/speech/tts

To create speech you need to supply the scriptId of the script you wish to generate, and the voice you would like to generate this request.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params
string
required

Reference to the Script that is to be synthesized, use /script to create and get it.

string
Defaults to Joanna

Either alias or original (provider's) ID. Available voices are listed at https://library.audiostack.ai/

float
Defaults to 1

Scalar for speed manipulation, range 0.5-3.

string

Amount of microseconds for silence padding. Half of the amount is inserted as silence at the beginning and at the end of each Speech file.

audience
object

Object defining the values for Script parameters. E.g. for Script parameters in:

<as:section name="main"> 
    Hello <as:placeholder id="username"> </as:placeholder>
    how's your <as:placeholder id="weekday"> </as:placeholder>
</as:section>

The object would be {"username": "Michael", "weekday": "Sunday"}.

sections
object

Separate configurations for Script section. E.g. to specify a separate voice and speed for Script section intro the object would be {"intro": {"voice": "Leah", "speed": 1.2}}.

boolean

Flag to apply lexicographical text corrections

boolean

Makes returned URLs publicly available

boolean

Flag to apply denoiser

boolean

Flag to apply autofix

Responses

Updated 7 months ago

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

Updated 7 months ago