Alibaba Cloud Model Studio:Audio and Video File Translation – Qwen

Python

import os
from openai import OpenAI
import base64
import numpy as np
import soundfile as sf

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region. For Beijing, use: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": {
                    "data": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                    "format": "wav",
                },
            }
        ],
    }
]

completion = client.chat.completions.create(
    model="qwen3-livetranslate-flash",
    messages=messages,
    modalities=["text", "audio"],
    audio={"voice": "Cherry", "format": "wav"},
    stream=True,
    stream_options={"include_usage": True},
    extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}},
)

# Concatenate Base64 fragments, then decode after the stream completes
audio_string = ""
for chunk in completion:
    if chunk.choices:
        if hasattr(chunk.choices[0].delta, "audio"):
            try:
                audio_string += chunk.choices[0].delta.audio["data"]
            except Exception as e:
                print(chunk.choices[0].delta.audio["transcript"])
    else:
        print(chunk.usage)

wav_bytes = base64.b64decode(audio_string)
audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
sf.write("output.wav", audio_np, samplerate=24000)

Node.js

import OpenAI from "openai";
import { createWriteStream } from "node:fs";
import { Writer } from "wav";

const client = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Singapore region. For Beijing, use: https://dashscope.aliyuncs.com/compatible-mode/v1
    baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
});

const messages = [
    {
        role: "user",
        content: [
            {
                type: "input_audio",
                input_audio: {
                    data: "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                    format: "wav",
                },
            },
        ],
    },
];

const completion = await client.chat.completions.create({
    model: "qwen3-livetranslate-flash",
    messages: messages,
    modalities: ["text", "audio"],
    audio: { voice: "Cherry", format: "wav" },
    stream: true,
    stream_options: { include_usage: true },
    translation_options: { source_lang: "zh", target_lang: "en" },
});

// Concatenate Base64 fragments, then decode after the stream completes
let audioString = "";
for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        if (chunk.choices[0].delta.audio?.data) {
            audioString += chunk.choices[0].delta.audio.data;
        }
    } else {
        console.log(chunk.usage);
    }
}

// Save as WAV file
async function saveAudio(base64Data, outputPath) {
    const wavBuffer = Buffer.from(base64Data, "base64");
    const writer = new Writer({
        sampleRate: 24000,
        channels: 1,
        bitDepth: 16,
    });
    const outputStream = createWriteStream(outputPath);
    writer.pipe(outputStream);
    writer.write(wavBuffer);
    writer.end();
    await new Promise((resolve, reject) => {
        outputStream.on("finish", resolve);
        outputStream.on("error", reject);
    });
    console.log(`Audio saved to ${outputPath}`);
}

saveAudio(audioString, "output.wav");

Python

Install pyaudio first:

import os
from openai import OpenAI
import base64
import numpy as np
import pyaudio
import time

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region. For Beijing, use: https://dashscope.aliyuncs.com/compatible-mode/v1
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "input_audio",
                "input_audio": {
                    "data": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                    "format": "wav",
                },
            }
        ],
    }
]

completion = client.chat.completions.create(
    model="qwen3-livetranslate-flash",
    messages=messages,
    modalities=["text", "audio"],
    audio={"voice": "Cherry", "format": "wav"},
    stream=True,
    stream_options={"include_usage": True},
    extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}},
)

# Initialize PyAudio for real-time playback
p = pyaudio.PyAudio()
stream = p.open(format=pyaudio.paInt16, channels=1, rate=24000, output=True)

for chunk in completion:
    if chunk.choices:
        if hasattr(chunk.choices[0].delta, "audio"):
            try:
                audio_data = chunk.choices[0].delta.audio["data"]
                wav_bytes = base64.b64decode(audio_data)
                audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
                stream.write(audio_np.tobytes())
            except Exception as e:
                print(chunk.choices[0].delta.audio["transcript"])

time.sleep(0.8)
stream.stop_stream()
stream.close()
p.terminate()

Node.js

Install dependencies first:

import OpenAI from "openai";
import Speaker from "speaker";

const client = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Singapore region. For Beijing, use: https://dashscope.aliyuncs.com/compatible-mode/v1
    baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
});

const messages = [
    {
        role: "user",
        content: [
            {
                type: "input_audio",
                input_audio: {
                    data: "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250211/tixcef/cherry.wav",
                    format: "wav",
                },
            },
        ],
    },
];

const completion = await client.chat.completions.create({
    model: "qwen3-livetranslate-flash",
    messages: messages,
    modalities: ["text", "audio"],
    audio: { voice: "Cherry", format: "wav" },
    stream: true,
    stream_options: { include_usage: true },
    translation_options: { source_lang: "zh", target_lang: "en" },
});

// Stream audio to speaker in real time
const speaker = new Speaker({
    sampleRate: 24000,
    channels: 1,
    bitDepth: 16,
    signed: true,
});

for await (const chunk of completion) {
    if (Array.isArray(chunk.choices) && chunk.choices.length > 0) {
        if (chunk.choices[0].delta.audio?.data) {
            const pcmBuffer = Buffer.from(chunk.choices[0].delta.audio.data, "base64");
            speaker.write(pcmBuffer);
        }
    } else {
        console.log(chunk.usage);
    }
}

speaker.on("finish", () => console.log("Playback complete"));
speaker.end();