tts.py

#!/usr/bin/env python3
"""
火山引擎 TTS Skill for OpenClaw
"""
import sys
import json
import os
import requests
import base64
import uuid
from pathlib import Path

def load_config():
    """加载配置文件"""
    script_dir = Path(__file__).parent
    config_path = script_dir / "config.json"
    
    if not config_path.exists():
        print("❌ 配置文件不存在，请先创建 config.json")
        print(f"参考: {script_dir / 'config.example.json'}")
        sys.exit(1)
    
    with open(config_path, 'r', encoding='utf-8') as f:
        return json.load(f)

def synthesize(text, voice=None, speed=None, volume=None, format=None, output=None):
    """合成语音"""
    config = load_config()
    
    # 使用默认值
    voice = voice or config.get("default_voice")
    speed = speed or config.get("default_speed", 1.0)
    volume = volume or config.get("default_volume", 1.0)
    format = format or config.get("default_format", "mp3")
    
    # 构建请求
    headers = {
        "Authorization": f"Bearer;{config['access_token']}",
        "Content-Type": "application/json"
    }
    
    payload = {
        "app": {
            "appid": config["appid"],
            "token": "access_token",
            "cluster": "volcano_tts"
        },
        "user": {
            "uid": "openclaw_user"
        },
        "audio": {
            "voice_type": voice,
            "encoding": format,
            "speed_ratio": float(speed),
            "loudness_ratio": float(volume),
            "rate": 24000
        },
        "request": {
            "reqid": str(uuid.uuid4()),
            "text": text,
            "operation": "query"
        }
    }
    
    # 发送请求
    api_url = config.get("api_url", "https://openspeech.bytedance.com/api/v1/tts")
    response = requests.post(api_url, headers=headers, json=payload, timeout=30)
    
    if response.status_code != 200:
        return {
            "success": False,
            "error": f"HTTP {response.status_code}: {response.text}"
        }
    
    result = response.json()
    
    if result.get("code") != 3000:
        return {
            "success": False,
            "error": f"错误码 {result.get('code')}: {result.get('message')}"
        }
    
    # 解码音频
    audio_data = base64.b64decode(result["data"])
    
    # 保存文件
    if not output:
        output = f"tts_output_{uuid.uuid4().hex[:8]}.{format}"
    
    output_path = Path(output)
    with open(output_path, "wb") as f:
        f.write(audio_data)
    
    duration = result.get("addition", {}).get("duration", "未知")
    
    return {
        "success": True,
        "file": str(output_path.absolute()),
        "duration_ms": duration,
        "voice": voice,
        "text": text
    }

def main():
    """命令行入口"""
    if len(sys.argv) < 2:
        print("用法: python tts.py <文本> [--voice 音色] [--speed 语速] [--volume 音量] [--format 格式] [--output 输出文件]")
        sys.exit(1)
    
    # 解析参数
    text = sys.argv[1]
    args = {}
    
    i = 2
    while i < len(sys.argv):
        if sys.argv[i].startswith("--"):
            key = sys.argv[i][2:]
            if i + 1 < len(sys.argv):
                args[key] = sys.argv[i + 1]
                i += 2
            else:
                i += 1
        else:
            i += 1
    
    # 合成
    result = synthesize(
        text=text,
        voice=args.get("voice"),
        speed=args.get("speed"),
        volume=args.get("volume"),
        format=args.get("format"),
        output=args.get("output")
    )
    
    # 输出结果
    print(json.dumps(result, ensure_ascii=False, indent=2))

if __name__ == "__main__":
    main()