minimax/voice-clone

POST

/openapi/v2/rhart-audio/text-to-audio/voice-clone

基于 Speech-02 与最新 Speech 2.6 HD/Turbo 系列打造的尖端声纹克隆引擎。它仅需数秒音频样本即可实现高保真的零样本克隆，精准复刻目标说话人的音色、口音与独特的叙事风格。该系统不仅支持全球 40 多种语言的跨语言流畅合成，更在情感表达力上实现了质的飞跃，允许开发者对语速、音高及情感色彩进行细粒度调节。凭借 Turbo 版本低于 250ms 的极低延迟性能，它成为了实时交互、沉浸式游戏及全球化品牌播报的理想音频解决方案。

请求参数

Authorization

Header 参数

Body 参数application/json必填

示例

{
    "audio": "https://www.runninghub.cn/view?filename=8ff07bf7a789afcbe91a8da77a07d2ef8d8137a65a6e60bb956a1d0fcbf319b7.wav&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzE0MDg4OTQ3MjksInRzIjoxNzcwODA0MDk0NzI5LCJzaWduIjoiZGI3MmMwZTgxYjM5ZmNkYzMxNzlkNDBmYTczNDE0ZWEifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.06611614675835809",
    "custom_voice_id": "Elegant_Man",
    "text": "基于 Speech-02 与最新 Speech 2.6 HD/Turbo 系列打造的尖端声纹克隆引擎。它仅需数秒音频样本即可实现高保真的零样本（Zero-shot）克隆，精准复刻目标说话人的音色、口音与独特的叙事风格。",
    "accuracy": 0.7,
    "need_noise_reduction": false,
    "need_volume_normalization": false,
    "model": "speech-02-hd"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/openapi/v2/rhart-audio/text-to-audio/voice-clone' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "audio": "https://www.runninghub.cn/view?filename=8ff07bf7a789afcbe91a8da77a07d2ef8d8137a65a6e60bb956a1d0fcbf319b7.wav&type=input&subfolder=&Rh-Comfy-Auth=eyJ1c2VySWQiOiIzZjY1MTNlNWEwNjY1N2I4OGYyNjU5NTEzYmU3ZDM0YyIsInNpZ25FeHBpcmUiOjE3NzE0MDg4OTQ3MjksInRzIjoxNzcwODA0MDk0NzI5LCJzaWduIjoiZGI3MmMwZTgxYjM5ZmNkYzMxNzlkNDBmYTczNDE0ZWEifQ==&Rh-Identify=3f6513e5a06657b88f2659513be7d34c&rand=0.06611614675835809",
    "custom_voice_id": "Elegant_Man",
    "text": "基于 Speech-02 与最新 Speech 2.6 HD/Turbo 系列打造的尖端声纹克隆引擎。它仅需数秒音频样本即可实现高保真的零样本（Zero-shot）克隆，精准复刻目标说话人的音色、口音与独特的叙事风格。",
    "accuracy": 0.7,
    "need_noise_reduction": false,
    "need_volume_normalization": false,
    "model": "speech-02-hd"
}'

返回响应

🟢200成功

application/json

任务结果查询接口：/openapi/v2/query

Body

示例

提交任务响应示例任务完成（查询状态接口）响应示例

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

修改于 2026-03-30 02:15:59

minimax/speech-2.8-turbo

可灵对口型-语音合成