anbeime/skill / skills/agentkit-multimedia-shopping/agentkit-multimedia-shopping
agentkit-multimedia-shopping
Verified电商运营与内容创作者在需要制作带货短视频时,用此技能一键生成9:16竖屏数字人成片。自动编排AI绘画、语音合成与视频生成,快速产出“小省导购员”专属形象与专业配音,让多模态视频制作省时省力。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.3 KB |
| assets/examples/sample-output.md | markdown | 6.8 KB |
| assets/templates/avatar-description.md | markdown | 1.6 KB |
| assets/templates/product-recommendation-script.md | markdown | 1.6 KB |
| references/character-profile.md | markdown | 5.1 KB |
| references/scene-templates.md | markdown | 5.5 KB |
| references/script-templates.md | markdown | 4.1 KB |
| references/tool-usage-guide.md | markdown | 5.3 KB |
| references/visual-styles.md | markdown | 5.0 KB |
| scripts/generate_audio.py | script | 9.3 KB |
| scripts/generate_character.py | script | 3.0 KB |
| scripts/generate_image.py | script | 6.3 KB |
| scripts/generate_music.py | script | 3.5 KB |
| scripts/generate_scene.py | script | 2.9 KB |
| scripts/generate_video.py | script | 4.5 KB |
| scripts/generate_voice.py | script | 3.5 KB |
scripts/generate_voice.py
View on GitHub#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
语音合成脚本
基于ByteDance agentkit-samples多媒体用例
"""
import sys
import os
def generate_voice(text, voice_type="standard", emotion="neutral", format="16khz_mono_wav"):
"""
合成导购员语音
Args:
text (str): 话术内容
voice_type (str): 语音类型(standard/friendly/professional),默认"standard"
emotion (str): 情绪基调(enthusiastic/professional/friendly),默认"neutral"
format (str): 音频格式(16khz_mono_wav),默认"16khz_mono_wav"
Returns:
object: 语音文件对象(根据实际工具返回)
Raises:
ValueError: 参数验证失败
Exception: 生成失败
"""
# 参数验证
if not text:
raise ValueError("话术内容不能为空")
if voice_type not in ["standard", "friendly", "professional"]:
raise ValueError("语音类型必须是standard/friendly/professional之一")
if emotion not in ["enthusiastic", "professional", "friendly", "neutral"]:
raise ValueError("情绪基调必须是enthusiastic/professional/friendly/neutral之一")
if format != "16khz_mono_wav":
raise ValueError("音频格式必须是16khz_mono_wav")
# TODO: 调用实际的TTS工具
# 这里需要根据ByteDance agentkit-samples的实际实现来调用
# 示例代码(伪代码):
#
# from agentkit import TTSGenerator
#
# generator = TTSGenerator()
# audio = generator.generate(
# text=text,
# voice_type=voice_type,
# emotion=emotion,
# format=format
# )
#
# return audio
# 占位符返回
print(f"[generate_voice] 合成语音")
print(f" 话术内容: {text[:50]}...")
print(f" 语音类型: {voice_type}")
print(f" 情绪基调: {emotion}")
print(f" 音频格式: {format}")
return None
def main():
"""
主函数:从命令行读取参数并合成语音
"""
import argparse
parser = argparse.ArgumentParser(description="合成导购员语音")
parser.add_argument("--text", type=str, required=True, help="话术内容")
parser.add_argument("--voice-type", type=str, default="standard", help="语音类型(standard/friendly/professional)")
parser.add_argument("--emotion", type=str, default="neutral", help="情绪基调(enthusiastic/professional/friendly)")
parser.add_argument("--format", type=str, default="16khz_mono_wav", help="音频格式(16khz_mono_wav)")
parser.add_argument("--output", type=str, default="./output/voice.wav", help="输出文件路径")
args = parser.parse_args()
try:
# 合成语音
voice_file = generate_voice(
text=args.text,
voice_type=args.voice_type,
emotion=args.emotion,
format=args.format
)
# 保存语音文件
if voice_file:
# 确保输出目录存在
output_dir = os.path.dirname(args.output)
if output_dir and not os.path.exists(output_dir):
os.makedirs(output_dir)
voice_file.save(args.output)
print(f"语音文件已保存至: {args.output}")
else:
print("警告: 语音合成返回为空(可能是占位符)")
return 0
except ValueError as e:
print(f"参数错误: {e}", file=sys.stderr)
return 1
except Exception as e:
print(f"生成失败: {e}", file=sys.stderr)
return 2
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |