Alibaba Cloud Model Studio:Traducción de archivos de audio y video – Qwen

qwen3-livetranslate-flash traduce archivos de audio y video en 18 idiomas. Acepta entrada de audio o video y devuelve texto traducido, audio sintetizado o ambos a través de una API de transmisión. Para entradas de video, el contexto visual mejora la precisión de la traducción (por ejemplo, distinguiendo entre "mascarilla médica" y "máscara de carnaval" basándose en los fotogramas del video).

Antes de comenzar

1. Crear una clave de API.
2. Configure la clave de API como variable de entorno.
3. (Opcional) Si utiliza el SDK de OpenAI, instale el SDK.

Inicio rápido

Todos los ejemplos utilizan la API de transmisión compatible con OpenAI. Establezca los idiomas de origen y destino mediante translation_options. La entrada predeterminada es audio; descomente el bloque de entrada de video en cada ejemplo para traducir archivos de video en su lugar.

Especificar source_lang mejora la precisión. Omítalo para habilitar la detección automática de idioma.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# --- Audio input ---
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",
                },
            }
        ],
    }
]

# --- Video input (uncomment to use) ---
# messages = [
#     {
#         "role": "user",
#         "content": [
#             {
#                 "type": "video_url",
#                 "video_url": {
#                     "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4"
#                 },
#             }
#         ],
#     },
# ]

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},
    # translation_options is not a standard OpenAI parameter; pass it through extra_body
    extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}},
)

for chunk in completion:
    print(chunk)

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
});

// --- Audio input ---
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",
                },
            },
        ],
    },
];

// --- Video input (uncomment to use) ---
// const messages = [
//     {
//         role: "user",
//         content: [
//             {
//                 type: "video_url",
//                 video_url: {
//                     url: "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241115/cqqkru/1.mp4",
//                 },
//             },
//         ],
//     },
// ];

async function main() {
    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" },
    });

    for await (const chunk of completion) {
        console.log(JSON.stringify(chunk));
    }
}

main();

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-livetranslate-flash",
    "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"
                    }
                }
            ]
        }
    ],
    "modalities": ["text", "audio"],
    "audio": {
        "voice": "Cherry",
        "format": "wav"
    },
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "translation_options": {
        "source_lang": "zh",
        "target_lang": "en"
    }
}'

Estos ejemplos utilizan una URL de archivo pública. Para utilizar un archivo local, consulte Ingresar un archivo local codificado en Base64.

Parámetros de solicitud

Entrada

El arreglo messages debe contener exactamente un mensaje con role establecido en user. El campo content contiene el audio o video a traducir:

• Audio: Establezca type en input_audio. Proporcione la URL del archivo o datos codificados en Base64 en input_audio.data, y especifique el formato (por ejemplo, wav) en input_audio.format.
• Video: Establezca type en video_url. Proporcione la URL del archivo en video_url.url.

Opciones de traducción

Especifique los idiomas de origen y destino en el parámetro translation_options:

"translation_options": {"source_lang": "zh", "target_lang": "en"}

En el SDK de Python, translation_options no es un parámetro estándar de OpenAI. Páselo a través de extra_body:

extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}}

Modalidad de salida

Controle el formato de salida con el parámetro modalities:

Cuando la salida incluye audio, establezca la voz en el parámetro audio. Consulte Voces admitidas para ver las opciones disponibles.

Restricciones

• Solo turno único: El modelo gestiona una traducción por solicitud. No se admiten conversaciones de múltiples turnos.
• Sin mensaje del sistema: El rol system no es compatible.
• Solo transmisión: Solo se admite la salida por transmisión compatible con OpenAI.

Analizar la respuesta

Cada objeto chunk de transmisión contiene:

• Texto: chunk.choices[0].delta.content
• Audio: chunk.choices[0].delta.audio["data"] (codificado en Base64, tasa de muestreo de 24 kHz)

Guardar audio en un archivo

Concatene todos los fragmentos de audio Base64 de la transmisión, luego decodifique y guarde el resultado una vez completada la transmisión.

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"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.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,
    // The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.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");

Reproducción en tiempo real

Decodifique cada fragmento Base64 a medida que llega y reprodúzcalo directamente. Este enfoque requiere bibliotecas de audio específicas de la plataforma.

Python

Instale pyaudio primero:

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"),
    # The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.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

Instale las dependencias primero:

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

const client = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following URL is for the Singapore region. When calling, replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.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();

Facturación

  video_tokens = ceil(frame_count / 2) x (height / 32) x (width / 32) + 2

# Install: pip install opencv-python
import math
import cv2

FRAME_FACTOR = 2
IMAGE_FACTOR = 32
MAX_RATIO = 200
VIDEO_MIN_PIXELS = 128 * 32 * 32
VIDEO_MAX_PIXELS = 768 * 32 * 32
FPS = 2
FPS_MIN_FRAMES = 4
FPS_MAX_FRAMES = 128
VIDEO_TOTAL_PIXELS = 16384 * 32 * 32

def round_by_factor(number, factor):
    return round(number / factor) * factor

def ceil_by_factor(number, factor):
    return math.ceil(number / factor) * factor

def floor_by_factor(number, factor):
    return math.floor(number / factor) * factor

def get_video(video_path):
    cap = cv2.VideoCapture(video_path)
    frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
    video_fps = cap.get(cv2.CAP_PROP_FPS)
    cap.release()
    return frame_height, frame_width, total_frames, video_fps

def smart_nframes(total_frames, video_fps):
    min_frames = ceil_by_factor(FPS_MIN_FRAMES, FRAME_FACTOR)
    max_frames = floor_by_factor(min(FPS_MAX_FRAMES, total_frames), FRAME_FACTOR)
    duration = total_frames / video_fps if video_fps != 0 else 0
    if duration - int(duration) > (1 / FPS):
        total_frames = math.ceil(duration * video_fps)
    else:
        total_frames = math.ceil(int(duration) * video_fps)
    nframes = total_frames / video_fps * FPS
    nframes = int(min(min(max(nframes, min_frames), max_frames), total_frames))
    if not (FRAME_FACTOR <= nframes <= total_frames):
        raise ValueError(f"nframes should in interval [{FRAME_FACTOR}, {total_frames}], but got {nframes}.")
    return nframes

def smart_resize(height, width, nframes, factor=IMAGE_FACTOR):
    min_pixels = VIDEO_MIN_PIXELS
    total_pixels = VIDEO_TOTAL_PIXELS
    max_pixels = max(min(VIDEO_MAX_PIXELS, total_pixels / nframes * FRAME_FACTOR), int(min_pixels * 1.05))
    if max(height, width) / min(height, width) > MAX_RATIO:
        raise ValueError(f"absolute aspect ratio must be smaller than {MAX_RATIO}, got {max(height, width) / min(height, width)}")
    h_bar = max(factor, round_by_factor(height, factor))
    w_bar = max(factor, round_by_factor(width, factor))
    if h_bar * w_bar > max_pixels:
        beta = math.sqrt((height * width) / max_pixels)
        h_bar = floor_by_factor(height / beta, factor)
        w_bar = floor_by_factor(width / beta, factor)
    elif h_bar * w_bar < min_pixels:
        beta = math.sqrt(min_pixels / (height * width))
        h_bar = ceil_by_factor(height * beta, factor)
        w_bar = ceil_by_factor(width * beta, factor)
    return h_bar, w_bar

def video_token_calculate(video_path):
    height, width, total_frames, video_fps = get_video(video_path)
    nframes = smart_nframes(total_frames, video_fps)
    resized_height, resized_width = smart_resize(height, width, nframes)
    video_token = int(math.ceil(nframes / FPS) * resized_height / 32 * resized_width / 32)
    video_token += 2
    return video_token

if __name__ == "__main__":
    video_path = "spring_mountain.mp4"  # Replace with your video path
    video_token = video_token_calculate(video_path)
    print("video_tokens:", video_token)

Para consultar los precios de tokens, consulte Lista de modelos.

Detalles del modelo

qwen3-livetranslate-flash actualmente tiene las mismas capacidades que qwen3-livetranslate-flash-2025-12-01.

Idiomas admitidos

Utilice estos códigos de idioma para source_lang y target_lang. Algunos idiomas de destino solo admiten salida de texto.

Voces admitidas

Establezca el parámetro voice en audio cuando la salida incluya audio sintetizado.

FAQ

Cuando ingreso un archivo de video, ¿qué contenido se traduce?

El modelo traduce la pista de audio del video. La información visual mejora la precisión de la traducción.

Por ejemplo, si el audio dice "Esto es una mascarilla":

• Cuando el video muestra una mascarilla médica, el modelo lo traduce como "Esto es una mascarilla médica".
• Cuando el video muestra una máscara de carnaval, el modelo lo traduce como "Esto es una máscara de carnaval".

Referencia de API

Para obtener detalles completos sobre los parámetros de entrada y salida, consulte Traducción de audio y video - Qwen.