Audio
Create Speech
Audio
Create Speech
Generate speech from text using the OpenAI API.
POST
/
v1
/
audio
/
speech
Body
application/json
input
string
requiredThe text to convert to speech.
voice
enum<string>
requiredThe voice to use for the speech, input should be 'nova', 'shimmer', 'echo', 'onyx', 'fable' or 'alloy'
Available options:
nova, shimmer, echo, onyx, fable, alloy model
enum<string>
requiredThe model to use for generating the speech. 'tts-1' is a high-quality model that is slower and more expensive, 'tts-1-hd' is a higher-quality model that is even slower and more expensive.
Read more about the models here.
Available options:
tts-1, tts-1-hd response_format
enum<string>
default: mp3The format of the audio response, defaults to mp3.
Available options:
mp3, opus, aac, flac, wav, pcm speed
number
default: 1The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
Response
200 - audio/mp3
The response is of type file.