python+阿里api实现ai数字人多国语言翻译Dubbing示例代码-python代码-BFW代码库

python+阿里api实现ai数字人多国语言翻译Dubbing示例代码

代码语言：python

所属分类：其他

代码描述：python+阿里api实现ai数字人多国语言翻译Dubbing示例代码，一个原声人物说话视频，设定目标翻译语言自动将这个人说话翻译成指定语言保持原音色说话的新视频

代码标签： python 阿里 api ai 数字人多国语言翻译 Dubbing 示例代码

下面为部分代码预览，完整代码请点击下载或在bfwstudio webide中打开

import os
import subprocess
import requests
import time
import uuid
import json
import asyncio
import httpx
import oss2
import dashscope
from dashscope.audio.tts_v2 import SpeechSynthesizer
from dashscope import Generation

# ================= 配置区 =================
# 1. 阿里云 OSS 配置

OSS_ACCESS_KEY_ID =""
OSS_ACCESS_KEY_SECRET =""
OSS_ENDPOINT ="oss-cn-beijing.aliyuncs.com"
OSS_BUCKET_NAME =""

# 拼接公网访问域名 (需确保 Bucket 已开启公共读权限)
OSS_PUBLIC_DOMAIN = f"https://{OSS_BUCKET_NAME}.{OSS_ENDPOINT}"

# 2. 阿里云 DashScope 配置
DASHSCOPE_API_KEY = os.getenv('DASHSCOPE_API_KEY', "sk-")
dashscope.api_key = DASHSCOPE_API_KEY

# 3. FFmpeg 路径
FFMPEG_PATH = 'ffmpeg'
# ==========================================

# ──────────────────────────────────────────────────────────
# 辅助函数：阿里云 DashScope 语音识别 (Paraformer 语音转文字)
# ──────────────────────────────────────────────────────────
async def dashscope_audiototxt(
    audio_url: str,
    api_key: str,
    http_client: httpx.AsyncClient,
    model: str = "paraformer-v2"
) -> dict:
    """异步提交语音识别任务，轮询进度，并拉取最终的 ASR 文字结果"""
    submit_url = "https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription"
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
        "X-DashScope-Async": "enable"
    }
    payload = {
        "model": model,
        "input": {"file_urls": [audio_url.strip()]}
    }

    print(">>> [ASR] 正在提交语音转文字任务...")
    resp = await htt.........完整代码请登录后点击上方下载按钮下载查看