GLM-TTS-Clone

声音克隆模型，可从 3 秒音频样本中学习说话人的音色。

Zhipu AIglm-tts-clone2025-12-11报告数据错误

规格

上下文: —
最大输出: —
输入价: —
输出价: ¥6/ 次
发布日期: 2025-12-11

上下文

官方未公布

价格 · CNY / 次

输入: —
输出: ¥6
缓存读取: —
缓存写入: —

输入输出

输入: 音频文本
输出: 音频

API

接口类型: audio

思考

官方未公布

源信息

状态: 可用
发布日期: 2025-12-11
知识截止: —

能力

官方未公布

调用方式

zhipumodel = glm-tts-clone

audio

POSThttps://open.bigmodel.cn/api/paas/v4/voice/clone

JSON

glm-tts-clone.json

{
  "id": "glm-tts-clone",
  "object": "model",
  "created": 1765411200,
  "owned_by": "zhipu",
  "name": "GLM-TTS-Clone",
  "api": {
    "types": [
      "audio"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "audio",
      "text"
    ],
    "output": [
      "audio"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": {
    "currency": "CNY",
    "unit": "request",
    "input": null,
    "output": 6,
    "cache_read": null,
    "cache_write": null
  },
  "features": [],
  "info": {
    "status": "active",
    "release_date": "2025-12-11",
    "knowledge_cutoff": null,
    "description": "Voice cloning model that learns a speaker's timbre from a 3-second audio sample.",
    "docs": "https://docs.bigmodel.cn/cn/guide/models/sound-and-video/glm-tts-clone",
    "verified_at": "2026-10-11"
  }
}

官方来源