MiniMax 短文本 V2

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

模型选择

model

enum<string>

模型选择

必需

枚举值:

MM_TTSL_realtime_speech-01-turboMM_TTSL_realtime_speech-01-240228MM_TTSL_realtime_speech-01-turbo-240228MM_TTSL_realtime_speech-02-turbo

示例值:

MM_TTSL_realtime_speech-01-turbo

voice_id

enum<string>

音色选择

必需

枚举值:

male-qn-qingsemale-qn-jingyingmale-qn-badaomale-qn-daxueshengfemale-shaonvfemale-yujiefemale-chengshufemale-tianmeipresenter_malepresenter_femaleaudiobook_male_1audiobook_male_2audiobook_female_1audiobook_female_2male-qn-qingse-jingpinmale-qn-jingying-jingpinmale-qn-badao-jingpinmale-qn-daxuesheng-jingpinfemale-shaonv-jingpinfemale-yujie-jingpinfemale-chengshu-jingpinfemale-tianmei-jingpinclever_boycute_boylovely_girlpeppa_pigbingjiao_didijunlang_nanyouchunzhen_xuedilengdan_xiongzhangbadao_shaoyetianxin_xiaolingqiaopi_mengmeiwumei_yujiediadia_xuemeidanya_xuejieSanta_ClausGrinchRudolphArnoldCharming_SantaCharming_LadySweet_GirlCute_ElfAttractive_GirlSerene_Womanmindcraft-58-7e8355d2b12145f488d068db04017f04

示例值:

male-qn-qingse

text

string

必需

通用参数语音合成文案

output_format

enum<string>

音频格式

可选

枚举值:

mp3wavpcmflacaac

示例值:

mp3

audio_sample_rate

enum<integer>

声音采样率

可选

枚举值:

160002400032000

示例值:

16000

speed

number

通用参数合成语速

可选

>= 0.5<= 2

默认值:

1

示例值:

1

volume

number

通用参数合成音量

可选

>= 1<= 10

默认值:

1

示例值:

1.5

bitrate

enum<integer>

声音的比特率

可选

枚举值:

3200064000128000

默认值:

32000

pitch

integer

声音语调

可选

>= -12<= 12

默认值:

0

timber_weights

array [object {2}]

混合音色

可选

voice_id

string

必需

minimax参数混合音色ID TTS 音色列表

weight

integer

必需

minimax参数混合音色权重

>= 1<= 100

channel

enum<integer>

音频的声道

可选

枚举值:

12

默认值:

1

示例值:

1

示例

{
    "model": "MM_TTSL_realtime_speech-01-turbo",
    "voice_id": "male-qn-qingse",
    "text": "你好啊，你叫什么名字",
    "output_format": "wav",
    "audio_sample_rate": 16000,
    "speed": 1,
    "volume": 0,
    "bitrate":32000
}

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": "MM_TTSL_realtime_speech-01-turbo",
    "voice_id": "male-qn-qingse",
    "text": "你好啊，你叫什么名字",
    "output_format": "wav",
    "audio_sample_rate": 16000,
    "speed": 1,
    "volume": 0,
    "bitrate":32000
}'

返回响应

🟢200成功

application/octet-stream

Body

id

string

请求ID

必需

使用 openai的py包 代码请求#

请求参数

示例代码

返回响应

使用 openai的py包代码请求