Colossyan API Documentation

Text to Speech

Text to Speech

We offer the option to listen to the voices with your custom text input.

Using the API

To post an audio generation job, you should send an authenticated POST request to the following endpoint.

The request body should have the following values:

text-YesstringThe text we want to turn into speech.
speaker_id-YesstringThe voice id of the desired speaker. See: voices
speed1NonumberThe talking speed of the speaker. Minimum: 0.9. Maximum: 1.1.
pitch1NonumberThe pitch of the voice. Minimum: 0.9. Maximum: 1.1.
pause0NonumberPause between sentences. Minimum: 0. Maximum: 5.

The response body will have the following values:

urlThe url to the generated audio file.
Edit this page on GitHub

On this page