阿里云语音合成CosyVoice

请求参数

Header 参数

Authorization

string

认证信息

必需

示例值:

Bearer {{api_key}}

Body 参数application/json

model

enum<string>

模型选择

必需

枚举值:

ALI_TTSL_realtime_cosyvoice-v1

示例值:

ALI_TTSL_realtime_cosyvoice-v1

voice_id

enum<string>

必需

音色选择 TTS 音色列表

枚举值:

longchenlongxionglongyulongjiaolongmeilongguilongpinglongpanglongwulongqilongxian_normallongfeifeilongxiulongdachuilongjiajialongjiayilongtaolongjiaxinlongchenglongzhelongnanlongyanlongqianglonghualongxinglongjinlonghanlongtianlongshuoloongstellalongxiaochenglongxiaoxialongxiaochunlongxiaobailonglaotielongyueloongbellalongshulongjinglongmiaolibailongwanlongkelonglinglongshaolongzelonghao

示例值:

longchen

text

string

语音合成文案

必需

speed

integer

声音语速

可选

>= -500<= 500

默认值:

0

volume

integer

声音音量

可选

>= 0<= 100

默认值:

50

output_format

enum<string>

音频格式

可选

枚举值:

pcmwavmp3

示例值:

pcm

audio_sample_rate

enum<integer>

声音采样率

可选

枚举值:

24000

默认值:

24000

示例值:

24000

pitch

integer

声音语调

必需

>= -500<= 500

默认值:

0

示例

{
  "model": "ALI_TTSL_realtime_cosyvoice-v1",
  "voice_id": "longchen",
  "text": "你好啊，你叫什么名字",
  "speed": 0,
  "volume": 50,
  "output_format": "mp3",
  "audio_sample_rate": 24000,
  "pitch": 283
}

示例代码

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location --request POST 'https://api.mindcraft.com.cn/v1/audio/speech' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "ALI_TTSL_realtime_cosyvoice-v1",
    "voice_id": "longchen",
    "text": "你好啊，你叫什么名字",
    "speed": 0,
    "volume": 50,
    "output_format": "mp3",
    "audio_sample_rate": 24000,
    "pitch": 283
}'

返回响应

🟢200成功

application/octet-stream

Body

id

string

请求ID

必需

阿里云 语音合成CosyVoice

使用 openai的py包 代码请求#

请求参数

示例代码

返回响应

阿里云语音合成CosyVoice

使用 openai的py包代码请求