给博客加上AI播客：用豆包TTS实现文章转双人对话语音

def build_frame(message_type, event, session_id, payload_bytes, flags=0b0100):
    # Header: 4字节
    #   byte0: version(4bit) + header_size(4bit) = 0x11
    #   byte1: message_type(4bit) + flags(4bit)
    #   byte2: serial_method(4bit) + compression(4bit)
    #   byte3: reserved
    header = bytes([0x11, (message_type << 4) | flags, 0x10, 0x00])

    # Optional: event(4字节) + session_id长度(4字节) + session_id
    optional = bytearray()
    if event is not None:
        optional.extend(struct.pack(">I", event))
    if session_id is not None:
        sid_bytes = session_id.encode('utf-8')
        optional.extend(struct.pack(">I", len(sid_bytes)))
        optional.extend(sid_bytes)

    # Payload
    frame = bytearray(header)
    frame.extend(optional)
    if payload_bytes is not None:
        frame.extend(struct.pack(">I", len(payload_bytes)))
        frame.extend(payload_bytes)

    return bytes(frame)

ws_headers = [
    f"X-Api-App-Id: {app_id}",
    f"X-Api-Access-Key: {access_key}",
    f"X-Api-Resource-Id: volc.service_type.10050",
    f"X-Api-App-Key: aGjiRDfUWi",
    f"X-Api-Request-Id: {uuid.uuid4()}"
]

ws = websocket.create_connection(
    "wss://openspeech.bytedance.com/api/v3/sami/podcasttts",
    timeout=60,
    header=ws_headers
)

payload = {
    "input_text": text,  # 文章全文
    "action": 0,
    "input_info": {
        "only_nlp_text": True,
        "input_text_max_length": 12000
    },
    "speaker_info": {
        "random_order": True,
        "speakers": [
            "zh_male_liufei_v2_saturn_bigtts",
            "zh_male_xiaolei_v2_saturn_bigtts"
        ]
    }
}

def modify_nlp_texts(nlp_texts, title=""):
    # 检查前3轮是否有开场白
    has_opening = any("欢迎收听" in t["text"] or "我是阿文" in t["text"]
                       for t in nlp_texts[:3])

    if not has_opening:
        first_speaker = nlp_texts[0]["speaker"]
        opening = f"欢迎收听阿文的播客，我是阿文。今天想跟大家聊聊这篇文章——《{title}》。"
        nlp_texts.insert(0, {"speaker": first_speaker, "text": opening})

    # 过滤掉太短的冗余句子
    filtered = [item for item in nlp_texts if len(item["text"].strip()) >= 10]

    return filtered

payload = {
    "action": 3,
    "nlp_texts": nlp_texts,
    "use_head_music": True,   # 开头音乐
    "use_tail_music": True,   # 结尾音乐
    "audio_config": {
        "format": "mp3",
        "sample_rate": 24000,
        "speech_rate": 0
    },
    "speaker_info": {
        "random_order": True,
        "speakers": ["zh_male_liufei_v2_saturn_bigtts", "zh_male_xiaolei_v2_saturn_bigtts"]
    }
}

def extract_article_text(file_path):
    # 移除 front matter
    content = re.sub(r'^---\s*\n.*?\n---\s*\n', '', content, flags=re.DOTALL)

    # 移除图片、链接、代码块、行内代码
    content = re.sub(r'!\[([^\]]*)\]\([^\)]+\)', '', content)
    content = re.sub(r'\[([^\]]+)\]\([^\)]+\)', r'\1', content)
    content = re.sub(r'```.*?```', '', content, flags=re.DOTALL)
    content = re.sub(r'`[^`]+`', '', content)

    # 移除标题标记、粗体斜体、HTML标签
    content = re.sub(r'^#+\s*', '', content, flags=re.MULTILINE)
    content = re.sub(r'[*_]{1,2}', '', content)
    content = re.sub(r'<[^>]+>', '', content)

    return content.strip()