语音 API已上线

elevenlabs-v3 API

ElevenLabs V3 已通过 API in One 接入真实生产路由 /api/v1/audio/speech，后端节点为 node58。一个 API Key 即可调用并按成功请求计费。

获取 API Key 查看文档

真实能力

以下能力来自当前已接入的模型配置和后端路由，不展示未上线 API。

稳定生产路由

Multi-character dialogue in a single request

统一接口

No separate ElevenLabs subscription needed

透明计费

30+ languages with automatic language detection

快速接入

Same API key for TTS, images, video, music, and chat

请求方式

浏览器端只调用同源 API，服务端 BFF 再转发到对应 Worker。

方法端点积分用途

POST/api/v1/audio/speech1 积分

Ultra-realistic text-to-speech with natural sounding voices. Supports multiple languages and voice styles.

参数

dialoguearray

Array of dialogue items: [{text: "...", voice: "..."}]. Voice is optional.

必填

stabilitynumber

Voice stability (0–1). Lower = more variation, higher = more consistent.

可选 · 默认 0.5

language_codestring

Language code (e.g. en, zh, ja) or "auto" for detection

可选 · 默认 auto

示例请求

{
  "endpoint": "/api/v1/audio/speech",
  "headers": {
    "Authorization": "Bearer <API_KEY>",
    "Content-Type": "application/json"
  },
  "body": {
    "model": "elevenlabs-v3",
    "dialogue": [
      {
        "text": "Hello, welcome to API in One.",
        "voice": "narrator"
      },
      {
        "text": "Thank you! Tell me more about this platform.",
        "voice": "user"
      }
    ],
    "stability": 0.5,
    "language_code": "auto"
  }
}

任务状态查询

图像、视频、音频和工具任务创建后，使用真实任务端点查询结果。

GET/api/v1/tasks/{task_id}查询生成任务状态和结果。

价格

1 credit minimum (~$0.01), then 28 credits per 1000 chars (~$0.28)

基础价格$0.01

积分1

计费按成功请求

使用场景

这些场景可通过当前模型和对应后端节点实现。

Generate multi-character dialogue for podcasts and audiobooks

Build voice-enabled chatbots and virtual assistants

Create audiobook content with multiple narrators

Generate multilingual voice content for global audiences

常见问题

How much does the ElevenLabs API cost through API in One?

Pricing is 28 credits per 1000 characters (~$0.28). The final cost scales with text length.

What languages does the ElevenLabs V3 API support?

ElevenLabs V3 supports 30+ languages. Set language_code to "auto" for automatic detection or specify a language code.

Can I create multi-voice dialogue?

Yes. The dialogue parameter accepts an array of objects, each with text and an optional voice. This enables multi-character conversations.

What is the stability parameter?

The stability parameter (0–1) controls voice consistency. Lower values (0.3) add more variation, higher values (0.8) produce more consistent output. Default is 0.5.