按模态浏览 PROMPTS

音频 Prompts — 37 个精选示例

面向 音频 生成工作流的 prompt 示例。按分类筛选,复制 prompt,或打开模型专属 API 代码。

AU
音频
dialogue text-to-dialogue-v3

Two-character interview dialogue

Host: Welcome back to the show. Today we're talking with Dr. Chen about the latest findings in marine biology. Doctor, you've spent six months in a submarine. What was the most surprising thing you saw down there? Dr. Chen: Honestly? The silence. People imagine the deep ocean is full of strange sounds, but at four thousand meters, it's the quietest place I've ever been. When we turned off all the equipment for calibration, the silence was so total it felt physical. Like pressure on your ears, but from the absence of sound rather than from water.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/elevenlabs/text_to_sound \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "text-to-dialogue-v3",
  "text": "Host: Welcome back to the show. Today we're talking with Dr. Chen about the latest findings in marine biology. Doctor, you've spent six months in a submarine. What was the most surprising thing you saw down there? Dr. Chen: Honestly? The silence. People imagine the deep ocean is full of strange sounds, but at four thousand meters, it's the quietest place I've ever been. When we turned off all the equipment for calibration, the silence was so total it felt physical. Like pressure on your ears, but from the absence of sound rather than from water."
}
JSON
常见问题

使用音频 prompts

好的%{model} prompt 应该包含什么?

有用的%{model} prompt 会清楚写出主体、风格、约束和输出目标。这里的示例足够短,便于复制;同时也足够具体,agent 或后端任务能保留生成意图。

这些 prompts 可以跨模型复用吗?

多数情况下可以。先从同一模态的 prompt 开始,再按模型调整画幅、时长、声音设置或风格控制。详情页会把保存过的参数列在 prompt 文本旁边。

在哪里找正确的模型 slug?

每张卡片都会显示 RunAPI 模型 slug。只想看一个模型的示例时,打开模型页;需要定价和能力细节时,进入模型目录页查看。

agent 可以直接调用这些 prompts 吗?

可以。安装 RunAPI MCP Server 后,复制 prompt 详情页里的 agent 指令。页面会把 prompt 文本、模型 slug 和 endpoint 路径放在一起,给 agent 足够上下文。