文本转语音(TTS)
curl --request POST \
--url https://openp.ai/v1/audio/speechimport requests
url = "https://openp.ai/v1/audio/speech"
response = requests.post(url)
print(response.text)const options = {method: 'POST'};
fetch('https://openp.ai/v1/audio/speech', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://openp.ai/v1/audio/speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://openp.ai/v1/audio/speech"
req, _ := http.NewRequest("POST", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://openp.ai/v1/audio/speech")
.asString();require 'uri'
require 'net/http'
url = URI("https://openp.ai/v1/audio/speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
response = http.request(request)
puts response.read_bodyOpenAI 兼容
文本转语音(TTS)
POST /v1/audio/speech —— 把文本合成为语音
POST
/
v1
/
audio
/
speech
文本转语音(TTS)
curl --request POST \
--url https://openp.ai/v1/audio/speechimport requests
url = "https://openp.ai/v1/audio/speech"
response = requests.post(url)
print(response.text)const options = {method: 'POST'};
fetch('https://openp.ai/v1/audio/speech', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://openp.ai/v1/audio/speech",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://openp.ai/v1/audio/speech"
req, _ := http.NewRequest("POST", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://openp.ai/v1/audio/speech")
.asString();require 'uri'
require 'net/http'
url = URI("https://openp.ai/v1/audio/speech")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
response = http.request(request)
puts response.read_body把文本合成为自然语音。
请求
curl https://openp.ai/v1/audio/speech \
-H "Authorization: Bearer $OPENPAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-1",
"input": "Hello from OpenPAI",
"voice": "alloy",
"response_format": "mp3"
}' --output speech.mp3
参数
| 字段 | 类型 | 必填 | 说明 |
|---|---|---|---|
model | string | ✅ | tts-1 / tts-1-hd / gpt-4o-mini-tts |
input | string | ✅ | 待合成文本(最长 4096 字符) |
voice | string | ✅ | 音色:alloy / echo / fable / onyx / nova / shimmer / coral / verse 等 |
response_format | string | mp3(默认) / opus / aac / flac / wav / pcm | |
speed | number | 0.25 - 4.0(默认 1.0) | |
instructions | string | gpt-4o-mini-tts 专属,可对语气 / 风格描述 |
响应
直接返回 二进制音频流,Content-Type 与所选 response_format 对应:
| response_format | Content-Type |
|---|---|
mp3 | audio/mpeg |
opus | audio/ogg |
aac | audio/aac |
flac | audio/flac |
wav | audio/wav |
pcm | audio/pcm |
Python 示例
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://openp.ai/v1")
with client.audio.speech.with_streaming_response.create(
model="tts-1-hd",
voice="nova",
input="OpenPAI 让大模型接入更简单。",
) as resp:
resp.stream_to_file("output.mp3")
gpt-4o-mini-tts 进阶
新一代 TTS 支持通过instructions 控制语气:
{
"model": "gpt-4o-mini-tts",
"voice": "coral",
"input": "今天的会议结果非常好。",
"instructions": "用兴奋、上扬的语气朗读,语速稍快。"
}
流式播放
合成时间可能 ≥ 1 秒,在浏览器或客户端可使用流式接收:with client.audio.speech.with_streaming_response.create(
model="tts-1",
voice="alloy",
input="...",
response_format="opus",
) as resp:
for chunk in resp.iter_bytes():
# 边收边播
play(chunk)