- 在线调用-使用说明
- 基础模型
- 大语言模型 LLM
- 语音识别 ASR
- 语音合成 TTS
- 图片生成 Images Generations
- 视频合成 Video Generations
- RAG模型
- 音色处理 voice processing
- 图生图 Image to Image
- 智能体
- 聊天机器人V3 AI角色(socket)
- AI桌面助手 V1 AI角色
- socket Device认证
- 对话数据
语音合成请求（汇总）
POST
https://api.mindcraft.com.cn/v1/audio/speech
提示
点击获取api_key
以下category(短文本)合成时 生成文件#
mm_tts_T2AV2
tx_tts_stdTone
tx_tts_premTone以下category(长文本)合成时 生成链接#
mm_tts_T2APro以下category(长文本)合成时 获得task_id#
tx_tts_longStdTone
tx_tts_longPrecTone使用 openai的py包 代码请求#
短文本合成语音
长文本合成(minimax)
长文本合成(腾讯)
请求参数
Header 参数
Authorization
string
认证信息
示例值:
Bearer {{api_key}}
Body 参数application/json
model
enum<string>
模型选择
枚举值:
MM_TTSL_realtime_speech-01-turboMM_TTSL_realtime_speech-01-240228MM_TTSL_realtime_speech-01-turbo-240228MM_TTSL_long_speech-01MM_TTSL_long_speech-02TX_TTS_realtimeTX_TTSP_realtimeTX_TTS_longTX_TTSP_longALI_TTSL_realtime_cosyvoice-v1ZJ_TTSL_realtimeXF_TTS_realtimeBD_TTS_realtime_zh
示例值:
MM_TTSL_realtime_speech-01-turbo
voice_id
string
必需
text
string
合成文案
speed
number
声音语速
>= 0.5<= 2
默认值:
1
示例值:
1
output_format
enum<string>
音频格式
枚举值:
mp3wavpcmflacaac
默认值:
mp3
示例值:
mp3
volume
number
可选
>= 1<= 10
默认值:
1
示例值:
1.5
audio_sample_rate
enum<integer>
可选
枚举值:
1600024000320008000
默认值:
24000
示例值:
16000
bitrate
enum<integer>
可选
枚举值:
3200064000128000
默认值:
32000
timber_weights
array [object {2}]
可选
voice_id
string
必需
weight
integer
必需
>= 1<= 100
pitch
integer
可选
>= -12<= 12
默认值:
0
示例值:
0
char_to_pitch
string
可选
示例值:
燕少飞/(yan4)(shao3)(fei1)omg/oh my god
channel
enum<integer>
可选
枚举值:
12
默认值:
1
示例值:
1
primary_language
enum<integer>
(腾讯) 语言类型
枚举值:
123
默认值:
1
示例值:
1
enable_subtitle
boolean
可选
默认值:
false
segment_rate
integer
可选
>= 0<= 2
默认值:
0
示例值:
0
emotion_category
enum<string>
(腾讯) 音频情感
枚举值:
neutralsadhappyangryfearnewsstoryradiopoetrycallsajiao厌恶amazepeacefulexcitingaojiaojieshuo
示例值:
neutral
emotion_intensity
integer
可选
>= 50<= 200
默认值:
50
示例值:
50
callback_url
string
可选
示例值:
https://cloud.tencent.com/document/product/1073/55746
over_dialogue
boolean
可选
默认值:
false
示例
{
"model": "MM_TTSL_realtime_speech-01-turbo",
"voice_id": "male-qn-daxuesheng",
"text": "燕少飞",
"speed": 1,
"output_format": "mp3",
"volume": 1.5,
"audio_sample_rate": 16000,
"bitrate": 128000
}示例代码
Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
请求示例请求示例
Shell
JavaScript
Java
Swift
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-daxuesheng",
"text": "燕少飞",
"speed": 1,
"output_format": "mp3",
"volume": 1.5,
"audio_sample_rate": 16000,
"bitrate": 128000
}'返回响应
🟢200成功
application/json
Body
id
string
请求ID
category
string
TTS 类型
model
string
必需
voice_id
string
TTS 音色
data
object
必需
category
string
TTS 类型
model
string
必需
voice_id
string
TTS 音色
word_count
integer
必 需
audio_file
string
音频链接
subtitle_file
string
必需
audio_length
integer
必需
audio_size
integer
必需
audio_sample_rate
integer
必需
bitrate
integer
必需
usage_characters
integer
必需
示例
{
"id": "ba03d8626a5643a0be8c3ef5ae9dc850",
"category": "mm_tts_T2APro",
"model": "speech-01",
"voice_id": "male-qn-qingse",
"data": {
"category": "mm_tts_T2APro",
"model": "speech-01",
"voice_id": "male-qn-qingse",
"word_count": 3,
"audio_file": "https://minimax-algeng-chat-tts.oss-cn-wulanchabu.aliyuncs.com/audio%2Ftts-wav-20240722143657-xoPtJbAN.wav?Expires=1721716617&OSSAccessKeyId=LTAI5tGLnRTkBjLuYPjNcKQ8&Signature=m9lqmAMGvykH1t%2FHCy4ayWFfFC8%3D",
"subtitle_file": "https://minimax-algeng-chat-tts.oss-cn-wulanchabu.aliyuncs.com/audio%2Ftts-wav-20240722143657-xoPtJbAN.title?Expires=1721716617&OSSAccessKeyId=LTAI5tGLnRTkBjLuYPjNcKQ8&Signature=UbRJiOHmyG7a1l%2BX07N1rN9vtO0%3D",
"audio_length": 1075,
"audio_size": 70046,
"audio_sample_rate": 16000,
"bitrate": 128000,
"usage_characters": 6
}
}🟢201task任务请求