Speech (Text-to-Speech)
將文本轉換為音訊,採用通用 Speech 協議格式。
POST https://wrouter.ai/v1/audio/speech請求體
| 引數 | 型別 | 必填 | 說明 |
|---|---|---|---|
model | string | ✓ | 如 tts-1、tts-1-hd、gpt-4o-mini-tts、cosyvoice-v1 |
input | string | ✓ | 待合成文本,<= 4096 字元 |
voice | string | ✓ | 如 alloy、echo、fable、onyx、nova、shimmer,或廠商專屬 voice |
response_format | string | mp3(預設)、opus、aac、flac、wav、pcm | |
speed | number | 語速,0.25 ~ 4.0,預設 1.0 |
響應
直接返回音訊二進位制流,Content-Type 為 audio/mpeg 等。
示例
bash
curl https://wrouter.ai/v1/audio/speech \
-H "Authorization: Bearer $WROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-1",
"input": "你好,我是 WRouter 的語音助手。",
"voice": "nova"
}' --output hello.mp3python
from pathlib import Path
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://wrouter.ai/v1")
resp = client.audio.speech.create(
model="tts-1-hd",
voice="alloy",
input="歡迎使用 WRouter 文字轉語音。",
)
Path("welcome.mp3").write_bytes(resp.content)