> ## Documentation Index
> Fetch the complete documentation index at: https://doc.xihuyun.com.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 语音接口 Audio

> 语音合成与语音识别

## 语音合成 TTS

**POST** `/v1/audio/speech`

| 参数                | 类型     | 必填 | 说明                                             |
| ----------------- | ------ | -- | ---------------------------------------------- |
| `model`           | string | 是  | 如 `tts-1`、`tts-1-hd`                           |
| `input`           | string | 是  | 待合成的文本                                         |
| `voice`           | string | 是  | `alloy`、`echo`、`fable`、`onyx`、`nova`、`shimmer` |
| `response_format` | string | 否  | `mp3`、`opus`、`aac`、`flac`                      |
| `speed`           | number | 否  | 0.25 \~ 4.0                                    |

```bash theme={null}
curl https://your-domain.com/v1/audio/speech \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"你好","voice":"alloy"}' \
  --output speech.mp3
```

## 语音识别 STT

**POST** `/v1/audio/transcriptions`

以 `multipart/form-data` 上传：

| 字段                | 必填 | 说明                        |
| ----------------- | -- | ------------------------- |
| `file`            | 是  | 音频文件                      |
| `model`           | 是  | 如 `whisper-1`             |
| `language`        | 否  | ISO-639-1                 |
| `response_format` | 否  | `json`、`text`、`srt`、`vtt` |

```bash theme={null}
curl https://your-domain.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-xxxx" \
  -F file="@audio.mp3" \
  -F model="whisper-1"
```