MOSS-TTSD音频合成

POST

/v1/audio/speech

最后修改时间：2025-10-14 11:56:18

fnlp/MOSS-TTSD-v0.5

高表现力语音：自然对话语调，支持情感表达

双人语音克隆：零样本克隆，自动切换说话人

中英双语支持：流畅混合合成，发音自然

长篇语音生成：低延迟，稳定输出长文本

请求参数

Header 参数

Body 参数application/json必填

示例

{
  "model": "fnlp/MOSS-TTSD-v0.5",
  "stream": true,
  "input": "[S1]Hello, how are you today?[S2]I'm doing great, thanks for asking![S1]That's wonderful to hear.",
  "references": [
    {
      "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Charles.mp3",
      "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦"
    },
    {
      "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Claire.mp3",
      "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦"
    }
  ],
  "max_tokens": 1600,
  "response_format": "mp3",
  "speed": 1,
  "gain": 0
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.aiznt.com/v1/audio/speech' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "fnlp/MOSS-TTSD-v0.5",
  "stream": true,
  "input": "[S1]Hello, how are you today?[S2]I'\''m doing great, thanks for asking![S1]That'\''s wonderful to hear.",
  "references": [
    {
      "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Charles.mp3",
      "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦"
    },
    {
      "audio": "https://sf-maas-uat-prod.oss-cn-shanghai.aliyuncs.com/voice_template/fish_audio-Claire.mp3",
      "text": "他又躺在那里，眼睛闭着，仍然沉浸在梦境的气氛里。那是个庞杂而亮堂的梦"
    }
  ],
  "max_tokens": 1600,
  "response_format": "mp3",
  "speed": 1,
  "gain": 0
}'

返回响应

🟢200成功

application/json

Body

示例

{"url":"https://cdn.aiznt.com/audio/2025/10/14/4280fb71-d86c-4527-9ddb-6815cf8fa29d.mp3"}

修改于 2025-10-14 11:56:18

文件上传

IndexTTS2音频合成

MOSS-TTSD音频合成

fnlp/MOSS-TTSD-v0.5#

请求参数

请求示例代码

返回响应

fnlp/MOSS-TTSD-v0.5