Speaking

Turns text into speech.

API Reference

POST https://api.geppetto.app/speak


Request Body

text

string

Required

The text to speak. Max length 512 characters

voice

string

Optional

Default: semaine

The voice to use

format

string

Optional

Default: mp3

The output format of the audio.

Supported formats are: mp3, wav, pcm, and ogg.

pcm outputs raw audio data in 16-bit signed integer format at 22050hz sampling rate in a single channel.

speed

number

Optional

Default: 1

The speed of the voice.

Values from 0.1 to 2.0 are supported

pitch

number

Optional

Default: 1

The pitch of the voice

sentenceSilence

number

Optional

Default: 150

The silence between sentences

Returns

The audio file content.

The content is streamed with Transfer-Encoding: chunked as soon as it becomes available.