TTS 文本转语音

NUWA 提供统一的文本转语音接口，聚合多家主流模型，保持与 OpenAI 风格一致的调用方式，适用于语音播报、AI 配音、数字人、智能客服、有声内容等场景。

支持的模型

gpt-4o-audio-preview：对话式音频生成，支持多模态输出（文本 + 音频）
gpt-4o-mini-tts：实时语音合成，支持通过提示词或 instructions 控制语音风格
tts-1-hd：高清音质的上一代 TTS 模型
tts-1：标准 TTS，兼顾质量与速度

性能建议：追求速度时使用 wav 或 pcm；高质量音频可选 tts-1-hd，实时应用推荐 gpt-4o-mini-tts。

接口规格

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(
    api_key="sk-***",  # 在 NUWA 控制台生成的 Key
    base_url="https://api.nuwaapi.com/v1"
)

with client.audio.speech.with_streaming_response.create(
    model="<model_id>",  # tts-1 / tts-1-hd / gpt-4o-mini-tts
    input="your text",
    voice="alloy",
    response_format="mp3",
) as response:
    response.stream_to_file("speech.mp3")

print("已保存到 speech.mp3")

const fs = require("fs");

async function main() {
  const response = await fetch("https://api.nuwaapi.com/v1/audio/speech", {
    method: "POST",
    headers: {
      "Authorization": "sk-***",
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "tts-1", // tts-1 / tts-1-hd / gpt-4o-mini-tts
      input: "your text",
      voice: "alloy",
      response_format: "mp3"
    })
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("speech.mp3", buffer);
  console.log("✅ 已保存到 speech.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.audio.speech.create({
    model: "tts-1", // tts-1 / tts-1-hd / gpt-4o-mini-tts
    input: "your text",
    voice: "alloy",
    response_format: "mp3"
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("speech.mp3", buffer);
  console.log("✅ 已保存到 speech.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

curl https://api.nuwaapi.com/v1/audio/speech \
  -H "Authorization: sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "your text",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3

echo "✅ 已保存到 speech.mp3"

model 为具体语音模型 ID
返回内容为音频二进制流

标准 TTS 参数（tts-1 / tts-1-hd / gpt-4o-mini-tts）

参数	类型	必填	说明
`model`	string	是	选择 `tts-1`、`tts-1-hd` 或 `gpt-4o-mini-tts`
`input`	string	是	待合成文本，最长约 4096 字符
`voice`	string	否	发音人：`alloy`、`echo`、`fable`、`onyx`、`nova`、`shimmer`
`response_format`	string	否	输出格式：`mp3`（默认）、`opus`、`aac`、`flac`、`wav`、`pcm`
`speed`	number	否	语速 0.25–4.0，默认 1.0；`gpt-4o-mini-tts` 不支持，可用自然语言控制
`instructions`	string	否	仅 `gpt-4o-mini-tts` 支持，用于指定口音、情绪、语调、语速等

gpt-4o-audio-preview 参数

参数	类型	必填	说明
`model`	string	是	设置为 `gpt-4o-audio-preview`
`modalities`	array	是	必须包含 `"text"` 和 `"audio"`
`audio`	object	是	音频配置，如 `{ "voice": "alloy", "format": "mp3" }`
`messages`	array	是	聊天消息数组，格式同标准 Chat Completions

调用示例

标准 TTS（tts-1）

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(api_key="sk-***", base_url="https://api.nuwaapi.com/v1")

with client.audio.speech.with_streaming_response.create(
    model="tts-1",
    input="欢迎使用 NUWA 文本转语音接口。",
    voice="alloy",
    response_format="mp3",
) as response:
    response.stream_to_file("speech.mp3")

print("已保存到 speech.mp3")

const fs = require("fs");

async function main() {
  const response = await fetch("https://api.nuwaapi.com/v1/audio/speech", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": "Bearer sk-***"
    },
    body: JSON.stringify({
      model: "tts-1",
      input: "欢迎使用 NUWA 文本转语音接口。",
      voice: "alloy",
      response_format: "mp3"
    })
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("speech.mp3", buffer);
  console.log("✅ 已保存到 speech.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.audio.speech.create({
    model: "tts-1",
    input: "欢迎使用 NUWA 文本转语音接口。",
    voice: "alloy",
    response_format: "mp3"
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("speech.mp3", buffer);
  console.log("✅ 已保存到 speech.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

curl https://api.nuwaapi.com/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "tts-1",
    "input": "欢迎使用 NUWA 文本转语音接口。",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3

echo "✅ 已保存到 speech.mp3"

gpt-4o-mini-tts（指定语音风格）

Python
JavaScript
TypeScript
Curl

from openai import OpenAI

client = OpenAI(api_key="sk-***", base_url="https://api.nuwaapi.com/v1")

with client.audio.speech.with_streaming_response.create(
    model="gpt-4o-mini-tts",
    input="请用温暖而清晰的声音播放这一段文字。",
    voice="nova",
    instructions="温柔、放松的语气，语速稍慢",
    response_format="mp3",
) as response:
    response.stream_to_file("soft.mp3")

print("已保存到 soft.mp3")

const fs = require("fs");

async function main() {
  const response = await fetch("https://api.nuwaapi.com/v1/audio/speech", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": "Bearer sk-***"
    },
    body: JSON.stringify({
      model: "gpt-4o-mini-tts",
      input: "请用温暖而清晰的声音播放这一段文字。",
      voice: "nova",
      instructions: "温柔、放松的语气，语速稍慢",
      response_format: "mp3"
    })
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("soft.mp3", buffer);
  console.log("✅ 已保存到 soft.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const response = await client.audio.speech.create({
    model: "gpt-4o-mini-tts",
    input: "请用温暖而清晰的声音播放这一段文字。",
    voice: "nova",
    // @ts-ignore
    instructions: "温柔、放松的语气，语速稍慢",
    response_format: "mp3"
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync("soft.mp3", buffer);
  console.log("✅ 已保存到 soft.mp3");
}

main().catch(e => console.error("❌ 出错：", e.message));

curl https://api.nuwaapi.com/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "请用温暖而清晰的声音播放这一段文字。",
    "voice": "nova",
    "instructions": "温柔、放松的语气，语速稍慢",
    "response_format": "mp3"
  }' \
  --output soft.mp3

echo "✅ 已保存到 soft.mp3"

gpt-4o-audio-preview（文本 + 音频）

Python
JavaScript
TypeScript
Curl

import base64
from pathlib import Path
from openai import OpenAI

client = OpenAI(api_key="sk-***", base_url="https://api.nuwaapi.com/v1")

completion = client.chat.completions.create(
    model="gpt-4o-audio-preview",
    modalities=["text", "audio"],
    audio={"voice": "alloy", "format": "mp3"},
    messages=[
        {"role": "user", "content": "用亲切的语气介绍一下 NUWA TTS 接口的用法。"}
    ],
)

# 文本结果（兼容 content 为空的情况）
msg = completion.choices[0].message
text_part = None
if msg.content and len(msg.content) > 0:
    first = msg.content[0]
    text_part = getattr(first, "text", None) if first is not None else None

if text_part:
    print(text_part)
else:
    print("未返回文本内容，完整 message 对象：", msg)

# 音频结果（Base64）写入 mp3
audio_b64 = completion.choices[0].message.audio.data
audio_bytes = base64.b64decode(audio_b64)
out_path = Path("preview.mp3")
out_path.write_bytes(audio_bytes)
print(f"音频已保存到 {out_path}")

const fs = require("fs");

async function main() {
  const response = await fetch("https://api.nuwaapi.com/v1/chat/completions", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": "Bearer sk-***"
    },
    body: JSON.stringify({
      model: "gpt-4o-audio-preview",
      modalities: ["text", "audio"],
      audio: { voice: "alloy", format: "mp3" },
      messages: [
        { role: "user", content: "用亲切的语气介绍一下 NUWA TTS 接口的用法。" }
      ]
    })
  });

  const data = await response.json();
  const msg = data.choices?.[0]?.message ?? {};
  const textPart = msg.content?.[0]?.text;
  if (textPart) {
    console.log(textPart);
  }

  const audioB64 = msg.audio?.data;
  if (audioB64) {
    fs.writeFileSync("preview.mp3", Buffer.from(audioB64, "base64"));
    console.log("音频已保存到 preview.mp3");
  } else {
    console.log("未返回音频数据：", JSON.stringify(data, null, 2));
  }
}

main().catch(e => console.error("❌ 出错：", e.message));

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "sk-***",
  baseURL: "https://api.nuwaapi.com/v1"
});

async function main(): Promise<void> {
  const completion = await client.chat.completions.create({
    model: "gpt-4o-audio-preview",
    modalities: ["text", "audio"] as any,
    audio: { voice: "alloy", format: "mp3" } as any,
    messages: [
      { role: "user", content: "用亲切的语气介绍一下 NUWA TTS 接口的用法。" }
    ]
  } as any);

  const msg: any = completion.choices?.[0]?.message ?? {};
  const textPart = msg.content?.[0]?.text;
  if (textPart) {
    console.log(textPart);
  }

  const audioB64 = msg.audio?.data;
  if (audioB64) {
    fs.writeFileSync("preview.mp3", Buffer.from(audioB64, "base64"));
    console.log("音频已保存到 preview.mp3");
  } else {
    console.log("未返回音频数据：", JSON.stringify(completion, null, 2));
  }
}

main().catch(e => console.error("❌ 出错：", e.message));

curl https://api.nuwaapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gpt-4o-audio-preview",
    "modalities": ["text", "audio"],
    "audio": {"voice": "alloy", "format": "mp3"},
    "messages": [
      {"role": "user", "content": "用亲切的语气介绍一下 NUWA TTS 接口的用法。"}
    ]
  }' -o response.json

python -c "
import json, base64
with open('response.json') as f:
    data = json.load(f)
msg = data.get('choices', [{}])[0].get('message', {})
audio = msg.get('audio', {}).get('data')
if audio:
    with open('preview.mp3', 'wb') as f:
        f.write(base64.b64decode(audio))
    print('音频已保存到 preview.mp3')
else:
    print('未返回音频数据:', json.dumps(data, ensure_ascii=False, indent=2))
"

返回说明

接口直接返回音频二进制流，建议使用 --output 或程序方式保存文件
若发生错误，将返回 JSON 结构的错误信息，包含状态码与原因

支持的模型​

接口规格​

标准 TTS 参数（tts-1 / tts-1-hd / gpt-4o-mini-tts）​

gpt-4o-audio-preview 参数​

调用示例​

标准 TTS（tts-1）​

gpt-4o-mini-tts（指定语音风格）​

gpt-4o-audio-preview（文本 + 音频）​

返回说明​

支持的模型

接口规格

标准 TTS 参数（tts-1 / tts-1-hd / gpt-4o-mini-tts）

gpt-4o-audio-preview 参数

调用示例

标准 TTS（tts-1）

gpt-4o-mini-tts（指定语音风格）

gpt-4o-audio-preview（文本 + 音频）

返回说明