音视频文件翻译-千问

import os
from openai import OpenAI

client = OpenAI(
    # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下为华北2（北京）地域的URL。请将 {WorkspaceId} 替换为您的百炼业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

# ----------------音频输入 ----------------
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",
                },
            }
        ],
    }
]

# ----------------视频输入(需取消注释)----------------
# 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},
    extra_body={"translation_options": {"source_lang": "zh", "target_lang": "en"}},
)

for chunk in completion:
    print(chunk)

# Installation instructions for pyaudio:
# APPLE Mac OS X
#   brew install portaudio
#   pip install pyaudio
# Debian/Ubuntu
#   sudo apt-get install python-pyaudio python3-pyaudio
#   or
#   pip install pyaudio
# CentOS
#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
# Microsoft Windows
#   python -m pip install pyaudio

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

# 初始化OpenAI客户端
client = OpenAI(
    # 若没有配置环境变量，请用阿里云百炼API Key将下行替换为：api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 以下为华北2（北京）地域的URL。请将 {WorkspaceId} 替换为您的百炼业务空间ID，各地域的URL不同。
    base_url="https://{WorkspaceId}.cn-beijing.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"}},
)

# 方式1: 待生成结束后再进行解码
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("audio_assistant_py.wav", audio_np, samplerate=24000)

# 方式2: 边生成边解码(使用方式2请将方式1的代码进行注释)
# # 初始化 PyAudio
# import pyaudio
# import time
# p = pyaudio.PyAudio()
# # 创建音频流
# 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_string = chunk.choices[0].delta.audio["data"]
#                 wav_bytes = base64.b64decode(audio_string)
#                 audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
#                 # 直接播放音频数据
#                 stream.write(audio_np.tobytes())
#             except Exception as e:
#                 print(chunk.choices[0].delta.audio["transcript"])

# time.sleep(0.8)
# # 清理资源
# stream.stop_stream()
# stream.close()
# p.terminate()