API reference

Speech

POST

/v1/audio/speech

Last modified:2025-02-05 11:13:45

了解如何将文本转换为音频。

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Header Params

Content-Type

string

required

Example:

application/json

Authorization

string

required

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

model

string

required

可用的 TTS 模型之一:tts-1 或 tts-1-hd

input

string

required

要生成音频的文本。最大长度为4096个字符。

voice

string

required

生成音频时使用的语音。支持的语音有:alloy、echo、fable、onyx、nova 和 shimmer。

response_format

string

optional

默认为 mp3 音频的格式。支持的格式有:mp3、opus、aac 和 flac。

speed

number

optional

默认为 1 生成的音频速度。选择0.25到4.0之间的值。1.0是默认值。

Example

{
  "model": "tts-1",
  "input": "The quick brown fox jumped over the lazy dog.",
  "voice": "alloy"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location -g --request POST '/v1/audio/speech' \
--header 'Authorization: Bearer ' \
--header 'Authorization;' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "tts-1",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy"
  }'

Responses

🟢200成功

application/json

Body

object {0}

Example

{
  "model": "tts-1",
  "input": "The quick brown fox jumped over the lazy dog.",
  "voice": "alloy"
}

Translations

DALL·E 3