OpenAI (TTS)
1. Overview
The industry's largest language model. Generates audio based on the input text.
Available model list:
tts-1
tts-1-hd
2. Request Description
Request method:
POST
Request address:
https://gateway.theturbo.ai/v1/audio/speech
3. Input Parameters
3.1 Header Parameters
Content-Type
string
Yes
Set the request header type, which must be application/json
application/json
Authorization
string
Yes
API_KEY required for authentication. Format: Bearer $YOUR_API_KEY
Bearer $YOUR_API_KEY
3.2 Body Parameters (application/json)
model
string
Yes
Model ID to use. See available models listed in the Overview for details, such as tts-1
.
tts-1
input
string
Yes
The text used to generate audio, with a maximum length of 4,096
characters.
hello, I'm Xiaoming
voice
string
Yes
The type of voice used to generate the audio. Support alloy
, ash
, coral
, echo
, fable
, onyx
, nova
, sage
, and shimmer
. (Official Docs)
alloy
response_format
string
No
The output format of the audio. Support mp3
, opus
, aac
, flac
, wav
, pcm
.
mp3
speed
number
No
The speech rate for generating the audio. The optional range is from 0.25
to 4.0
. 1.0
4. Request Example
5. Response Example
Last updated