返回首页Back to Home
能用。但安装很痛苦。这是完整指南。 It Works. The Setup Hurts. Here's Everything.

MoneyPrinterTurbo: 免费AI视频生成器 — 安装指南 + Bug修复Setup Guide, Bug Fixes & Honest Review

花了1.5小时,经历了4次git clone失败、moviepy版本冲突、装错了一个没有界面的版本——我终于生成了第一个视频。这是我希望开始之前就有人写好的指南。 After 1.5 hours, 4 failed git clones, a moviepy version conflict, and a version that had no GUI — I finally made a video. This is the guide I wish existed when I started.

跳到真实安装指南 ↓ Skip to Real Setup Guide ↓

MoneyPrinterTurbo 是什么?安装前必读What Is MoneyPrinterTurbo? Read Before Installing

MoneyPrinterTurbo 是一个开源的 AI 工具,可以根据一句话自动生成视频。你给它一个主题(例如"关于黑洞的5个冷知识"),它会自动生成完整视频——包括文案、配音、画面、字幕和背景音乐——完全不需要你动手剪辑。 MoneyPrinterTurbo is an open-source AI tool that automatically generates videos from a single sentence. You give it a topic (e.g. "Top 5 facts about black holes") and it produces a complete video — script, voiceover, visuals, subtitles, and background music — without you touching a timeline.

由国内开发者 harry0703 创建,因"第一个真正一键式 AI 视频生成流水线"在 GitHub 上爆火。 It was built by a Chinese developer (harry0703) and gained massive traction on GitHub for being the first truly one-click AI video pipeline that runs locally.

72,000+ GitHub 星标stars on GitHub

效果一览Results At A Glance

我用提示词 "东京必去的3个地方" 进行了测试。以下是 AI 生成视频与手动剪辑的对比: I tested it with the prompt "Top 3 things to do in Tokyo". Here's what came out, side by side with a manually-edited video for comparison:

MPT generated video still
AI 生成(MPT)— 约 60 秒完成 AI-Generated (MPT) — ~60s to produce
Manually edited video reference
手动剪辑 — 约 30 分钟完成 Manually Edited — ~30min to produce
对比维度CriteriaMoneyPrinterTurbo手动剪辑Manual Editing
1分钟视频耗时Time to produce 1-min video~60 秒~60 seconds~30 分钟~30 minutes
画面质量Visual quality不错(素材库拼接)Good (stock footage)取决于剪辑水平Depends on skill
配音质量Voiceover quality良好(Edge TTS,免费)Good (Edge TTS, free)需要录音设备Needs recording/mic
自定义程度Customization限于模板参数Limited to templates完全自由Full control
单条视频成本Cost per video~$0.01(API 费用)~$0.01 (API fees)时间 + 软件订阅Time + subscription

要钱吗?Is It Free?

简单回答:完全免费,零 API Key 也可用。前提是使用 v1.1.0 + g4f 配置(见下方指南)。 The short answer: yes, completely free. Zero API keys required. If you use v1.1.0 + the g4f config shown below.

v1.1.0 + g4f + Edge TTSv1.1.0 + g4f + Edge TTS

$0
  • g4f = 免费 LLM 写文案
  • g4f = free LLM for script writing
  • Edge TTS = 免费配音(Windows 内置)
  • Edge TTS = free voiceover (built into Windows)
  • Pexels = 免费素材(无需 API Key)
  • Pexels = free stock footage (no API key needed)
  • 不需要信用卡。不需要注册。没有任何配额限制。
  • No credit card. No registration. No quota limits.
给 v1.2.x 用户的提醒:最新版本去掉了 Edge TTS 支持,需要 Azure API Key。如果你看到页面让你填 Azure 密钥,说明你装错版本了。用 v1.1.0。 Heads-up for v1.2.x users: The latest version dropped Edge TTS support and requires Azure API keys. If you see a page asking for Azure credentials, you grabbed the wrong version. Use v1.1.0.

真实安装指南 (Bug修复 + 避坑)Real Setup Guide — Bug Fixes & Workarounds

每个教程都说"又快又简单"。以下是真正有效的步骤,包括所有别人跳过不谈的部分。每步标注了适用范围: Every tutorial says "quick and easy." Here's what actually works. Each step tagged so you know what affects you:

📖 需要独立的安装教程?MoneyPrinterTurbo 安装指南(10分钟完整版) 📖 Want a standalone tutorial? MoneyPrinterTurbo Setup Guide (10-Minute Complete)

🎬 装好了?怎么用 MoneyPrinterTurbo 做出第一个视频 → 🎬 Already installed? How to use MPT and make your first video →

GLOBAL 全球通用,谁都会遇到Happens to everyone, everywhere  |  REGIONAL 仅限中国/受限网络用户China / restricted-network users only

  1. GLOBAL 选对版本Pick the RIGHT version
    最新版(v1.2.9)没有 Web 界面,只有 API。新手必须用旧版: The latest release (v1.2.9) is API-only — no Web UI. Beginners must use the old version:
    git clone --branch v1.1.0 --depth 1 https://github.com/harry0703/MoneyPrinterTurbo.git
    cd MoneyPrinterTurbo
    REGIONAL 开启 VPN — GitHub 连接经常被重置。--depth 1 减少下载量规避中断。VPN ON for git clone — GitHub connections reset frequently through GFW. --depth 1 minimizes the pain.
  2. GLOBAL 安装依赖Install dependencies
    需要 Python 3.10+。建议使用镜像源加速: Python 3.10+ required. Use a mirror for speed:
    pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
    GLOBAL 如果报错 "moviepy.editor not found":pip install moviepy==1.0.3 — v2.0.0 破坏了 MPT v1.1.0 依赖的 API。If you get "moviepy.editor not found": pip install moviepy==1.0.3 — v2.0.0 broke the API MPT v1.1.0 depends on.
    REGIONAL 关闭 VPN — 阿里云镜像在国内直连更快。VPN OFF for pip — Aliyun mirror is faster from within China.
  3. GLOBAL 30 秒配好配置Configure in 30 seconds
    复制 config.example.tomlconfig.toml。只改一行: Copy config.example.tomlconfig.toml. Change ONE line:
    llm_provider = "g4f"
    搞定。g4f = 免费 AI 写文案。Edge TTS = 免费配音。不要 API Key。不用注册 Azure。不用绑定信用卡。 That's it. g4f = free AI. Edge TTS = free voiceover. No API keys. No credit card. Works anywhere.
  4. GLOBAL 先启动后端Launch the BACKEND first
    打开 PowerShell 窗口 #1:Open PowerShell #1:
    cd D:\Projects\MoneyPrinterTurbo
    python main.py
    看到 "start server, docs: http://127.0.0.1:8080/docs" 就对了。这个窗口不要关。 Wait for "start server, docs: http://127.0.0.1:8080/docs". Do NOT close this window.
    macOS/Linux:用终端代替 PowerShell,路径用 / 不用 \。macOS/Linux: use Terminal instead of PowerShell, paths use / not \.
  5. GLOBAL 再启动前端Launch the FRONTEND
    打开 PowerShell 窗口 #2:Open PowerShell #2:
    cd D:\Projects\MoneyPrinterTurbo
    streamlit run .\webui\Main.py
    浏览器自动打开 http://localhost:8501。输入主题,点生成。 Browser opens at http://localhost:8501. Type a topic, click Generate.
    REGIONAL 如果卡在"下载素材"那一步,开启 VPN — Pexels 在国内被墙。VPN ON if it hangs at "downloading materials" — Pexels is blocked in China.
总结:5 步中有 3 步存在全球性的坑(版本选择、moviepy 冲突、双终端架构),2 步受中国网络环境影响(git clone 稳定性、pip 速度、Pexels 访问)。即使没有墙,首次安装至少 30 分钟。官方文档一个字没提这些。 Bottom line: 3 of 5 steps have GLOBAL issues (version choice, moviepy conflict, dual-terminal architecture). 2 of 5 have REGIONAL issues (git clone stability, pip speed, Pexels access). Even without the GFW, this setup would still take 30+ minutes the first time. The official docs skip everything you just read.

资源链接Resources & Links

常见问题MoneyPrinterTurbo FAQ — Setup, Errors & Free Usage

新手用 v1.1.0。有 Streamlit 图形界面(点点就行),内置 Edge TTS(免费配音),支持 g4f(免费 AI)。v1.2.x 是完全重写版——纯 FastAPI、没有界面、需要外部 API Key。适合开发者做流水线集成;对只想生成一个视频的人来说是灾难。 v1.1.0 for beginners. It has a Streamlit Web UI (point-and-click), built-in Edge TTS (free voiceover), and g4f support (free AI). v1.2.x is a complete rewrite — FastAPI-only, no GUI, requires external API keys. Great for developers building pipelines; terrible for someone who just wants to make a video.

仓库比较大。两个解决办法:(1) 用 --depth 1 浅克隆——跳过历史记录,下载量减少 80%。(2) 如果不在美国,开 VPN——部分地区到 GitHub 的连接会频繁重置。黄金命令:git clone --branch v1.1.0 --depth 1 https://github.com/harry0703/MoneyPrinterTurbo.git The full repo is large. Two fixes: (1) Use --depth 1 for a shallow clone — skips git history, reduces download by 80%. (2) Turn on your VPN if you're outside the US — GitHub connections from some regions reset frequently. The magic command: git clone --branch v1.1.0 --depth 1 https://github.com/harry0703/MoneyPrinterTurbo.git

moviepy 2.0 移除了 MPT v1.1.0 依赖的 moviepy.editor 模块。修复:pip install moviepy==1.0.3。因为 requirements.txt 没有锁定精确版本。 moviepy 2.0 removed the moviepy.editor module that MPT v1.1.0 depends on. Fix: pip install moviepy==1.0.3. This happens because requirements.txt doesn't pin an exact version.

MPT v1.1.0 把后端(FastAPI,负责视频渲染)和前端(Streamlit,你看到的界面)拆成了两个独立进程。后端用 python main.py 启动(端口 8080),前端用 streamlit run webui/Main.py 启动(端口 8501)。两个都需要跑着。生成视频期间两个窗口都别关。 MPT v1.1.0 splits the backend (FastAPI, handles video rendering) and frontend (Streamlit, the UI you see) into separate processes. The backend runs on python main.py (port 8080), the frontend on streamlit run webui/Main.py (port 8501). You need both running. Keep both windows open while making videos.

能用——但要管理好预期。它不会从零生成 AI 视频(像 Sora 那样)。它是把素材片段 + AI 配音 + 字幕拼接成一个精致的幻灯片式视频。效果像一个不错的 YouTube 科普视频。适合无出镜内容频道、教程、社媒短视频。不适合创意电影或动画。 Yes — but set expectations. It doesn't generate AI video from scratch (like Sora). It assembles stock footage + AI voiceover + subtitles into a polished slideshow-video. The result looks like a decent YouTube explainer. Perfect for faceless content channels, tutorials, and social media clips. Not suitable for cinematic or creative video projects.

git clone:开 VPN(部分地区 GitHub 被墙/不稳定)。pip install:关 VPN + 用镜像如 https://mirrors.aliyun.com/pypi/simple/——VPN 会让 pip 慢到怀疑人生。生成视频:开 VPN——Pexels 素材下载不走 VPN 经常失败。 Git clone: VPN ON (GitHub is blocked/unstable from some regions). pip install: VPN OFF + use a mirror like https://mirrors.aliyun.com/pypi/simple/ — VPN will slow pip to a crawl. Generating videos: VPN ON — Pexels stock footage downloads often fail without it.

不需要。MPT 不在本地跑 AI 模型——它调用云端 API 或素材服务。一切都在 CPU 上运行。一个普通笔记本就够。"faster-whisper" 依赖只在开启 Whisper 字幕时才会用到(默认关闭)。 No. MPT doesn't run local AI models — it calls cloud APIs or stock services. Everything runs on CPU. A basic laptop is sufficient. The "faster-whisper" dependency is only used if you enable Whisper subtitles (off by default).

MPT 本身是 MIT 协议——无限制。Pexels 素材可免版税商用。Edge TTS 配音免费商用。如果你改用 Azure TTS 或 OpenAI,请查看各自的服务条款。结论:用免费配置(g4f + Edge TTS + Pexels)生成的视频,商用没问题。 MPT itself is MIT-licensed — no restrictions. Stock footage from Pexels is royalty-free. Edge TTS voices are free for commercial use. If you switch to Azure TTS or OpenAI, check their terms. Bottom line: with the free setup (g4f + Edge TTS + Pexels), you're clear for commercial use.

MoneyPrinterTurbo 常见错误 & 修复MoneyPrinterTurbo Bugs & Troubleshooting

我在 Windows 11(中国网络环境)上花了 ~4 小时才让 MPT v1.1.0 生成出一个视频。每一步都踩了坑。以下按类别整理了全部 18 个 bug——含症状、根因、修复代码。 I spent ~4 hours getting MPT v1.1.0 to generate one video on Windows 11 (China). Every single step hit an issue. Below are all 18 bugs — with symptoms, root causes, and fix code — organized by category.

小白路径Beginner Path程序员路径Programmer Path
MPT 版本Versionv1.1.0 (Streamlit Web UI)v1.2.9 (API-only, CLI)
LLMQwen (DashScope/Bailian) — 免费、国内直连free, China-direct任意 OpenAI 兼容服务Any OpenAI-compatible provider
界面Interface浏览器 localhost:8501Browser at localhost:8501curl / 自定义脚本custom scripts
预计耗时(修复后)Expected Time (after fixes)~30 min~15 min
实际耗时(中国)Reality (China)2–4 小时hours1–2 小时hours
🌐 网络与环境🌐 Network & Environment 5 bugs
Symptom / 症状
RPC failed, early EOF, fetch-pack unexpected disconnect
Root Cause / 根因
GitHub 在国内被限速/阻断;完整仓库体积较大 GitHub blocked/throttled in China; full repo is large
Fix / 修复
git clone --branch v1.1.0 --depth 1 https://github.com/harry0703/MoneyPrinterTurbo.git
浅克隆 + 指定分支,跳过全部历史记录,减少约 80% 下载量 Shallow clone + specific branch, skips all history, ~80% less data
Symptom / 症状
pip install -r requirements.txt 卡住不动或超时hangs or times out
Root Cause / 根因
清华镜像限速Tsinghua mirror throttling
Fix / 修复
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
换用阿里云镜像Switch to Aliyun mirror
Symptom / 症状
GitHub/Pexels/Edge TTS 需要 VPN 开,pip 镜像需要 VPN 关——反复横跳 Need VPN ON for GitHub/Pexels/Edge TTS, VPN OFF for pip mirrors — constant toggling
Root Cause / 根因
分流路由问题:国内镜像不走 VPN 才能快,海外服务不走 VPN 连不上 Split routing: China mirrors need direct connection, overseas services need VPN
Fix / 修复
使用分隧道 VPN(Clash/V2Ray);没有的话手动切换: Use split-tunnel VPN (Clash/V2Ray); if unavailable, toggle manually:
VPN 开 → git clone / Pexels 素材 / Edge TTSVPN ON → git clone / Pexels / Edge TTS
VPN 关 → pip install(镜像源)VPN OFF → pip install (mirrors)
Symptom / 症状
WSServerHandshakeError: 403, message='Invalid response status' 来自 speech.platform.bing.com
Root Cause / 根因
微软 Bing 语音服务在国内被墙Microsoft Bing Speech service is blocked in China
Fix / 修复
必须开 VPN。同时升级 edge-tts:VPN ON required. Also upgrade edge-tts:
pip install edge-tts --upgrade
完整修复指南:为什么被墙、VPN 开关策略、替代方案 Full fix guide: why it's blocked, VPN strategy, alternatives
Symptom / 症状
字幕功能回退到 Whisper,从 Hugging Face 下载 large-v3 模型(~3GB)——国内极慢 Subtitle fallback to Whisper downloads large-v3 model (~3GB) from Hugging Face — extremely slow in China
Root Cause / 根因
Edge TTS 字幕创建因 SentenceBoundary-only chunks + 匹配逻辑不兼容而失败,回退到 Whisper;Hugging Face 在国内被限速 Edge TTS subtitle creation fails (SentenceBoundary-only + matching incompatibility), falling back to Whisper; HF throttled in China
Fix / 修复
在 Streamlit 中取消勾选"启用字幕",完全跳过 Whisper。或通过 HF 镜像站预下载模型 Uncheck "Enable Subtitles" in Streamlit to skip Whisper entirely. Or pre-download model via HF mirror
📦 版本与依赖地狱📦 Version & Dependency Hell 2 bugs
Symptom / 症状
装了最新版,只有 /docs API 页面,没有 Streamlit 界面 Installed latest, only /docs API page, no Streamlit UI
Root Cause / 根因
v1.2.x 移除了 Streamlit Web UI,纯 API 版本 v1.2.x dropped the Streamlit Web UI, API-only
Fix / 修复
git checkout v1.1.0
v1.1.0 是最后一个有图形界面的版本。→ 完整修复指南:为什么没有界面、如何切换、v1.1.0 vs v1.2.x 对比v1.1.0 is the last version with a Web UI. → Full fix guide: why there's no GUI, how to switch, v1.1.0 vs v1.2.x comparison
Symptom / 症状
ModuleNotFoundError: No module named 'moviepy.editor'
Root Cause / 根因
moviepy v2.0.0 移除了 MPT v1.1.0 依赖的 moviepy.editor 模块 moviepy v2.0.0 removed the moviepy.editor module that MPT v1.1.0 depends on
🎬 moviepy API 变更🎬 moviepy Breaking Changes 2 bugs
Symptom / 症状
write_videofile() got an unexpected keyword argument 'temp_audiofile_path'
Root Cause / 根因
moviepy v1.0.3 参数名是 temp_audiofile 而非 temp_audiofile_path moviepy v1.0.3 uses temp_audiofile not temp_audiofile_path
Fix / 修复
app/services/video.py 中全局替换Replace all occurrences in app/services/video.py
temp_audiofile_path  →  temp_audiofile
Symptom / 症状
Unable to choose an output format for 'D:\...\tasks\<uuid>'
Root Cause / 根因
temp_audiofile 被设为目录路径而非文件路径(缺少扩展名) temp_audiofile was set to a directory path instead of a file path with extension
Fix / 修复
video.py 第 109、256 行In video.py lines 109, 256
temp_audiofile=output_dir
→ temp_audiofile=os.path.join(output_dir, "temp_audio.m4a")
🔊 edge-tts API 重大变更(5连坑)🔊 edge-tts Breaking Changes (5-in-a-row) 5 bugs
Symptom / 症状
ImportError: cannot import name 'mktimestamp' from 'edge_tts.submaker'
Root Cause / 根因
edge-tts 升级后移除了 mktimestamp 工具函数 edge-tts package upgraded and removed the mktimestamp utility function
Fix / 修复
app/services/voice.py 第5行添加本地实现:Add local implementation to app/services/voice.py line 5:
def mktimestamp(seconds: float) -> str:
    hrs = int(seconds // 3600)
    mins = int((seconds % 3600) // 60)
    secs = int(seconds % 60)
    millis = int((seconds % 1) * 1000)
    return f"{hrs:02d}:{mins:02d}:{secs:02d}.{millis:03d}"
Symptom / 症状
'SubMaker' object has no attribute 'subs'
Root Cause / 根因
edge-tts 将 .subs 重命名为 .cues(返回 Subtitle 对象列表而非字符串) edge-tts renamed .subs.cues (list of Subtitle objects instead of strings)
Fix / 修复
voice.pyIn voice.py:
# Line 1017:
sub_maker.subs  →  sub_maker.cues

# Line 1087: replace zip(sub_maker.offset, sub_maker.subs)
# with iteration over sub_maker.cues, using
# .content for text and .start/.end.total_seconds() for timestamps
Symptom / 症状
'SubMaker' object has no attribute 'offset'
Root Cause / 根因
edge-tts 移除了 .offset,时间戳现在在 Subtitle.start / .end(timedelta 对象) edge-tts removed .offset, timestamps now in Subtitle.start/.end as timedelta objects
Fix / 修复
voice.pyget_audio_duration()(约1125行):In get_audio_duration() (~line 1125):
def get_audio_duration(sub_maker):
    if not sub_maker.cues:
        return 0.0
    return sub_maker.cues[-1].end.total_seconds()
Symptom / 症状
sub_maker.cues is None (流式结束后无字幕填充)(no cues populated after streaming)
Root Cause / 根因
旧 API:sub_maker.create_sub((offset, duration), text)。新 API:sub_maker.feed(chunk)——直接传入原始 chunk 字典 Old API: sub_maker.create_sub((offset, duration), text). New API: sub_maker.feed(chunk) — takes raw chunk dict
Fix / 修复
voice.py _do() 函数(约1013行):In voice.py _do() function (~line 1013):
# Old:
sub_maker.create_sub((chunk["offset"], chunk["duration"]), chunk["text"])
# New:
sub_maker.feed(chunk)
Symptom / 症状
sub_maker.cues is None (即使 feed() 修好后仍然为空)(still empty even after feed() fix)
Root Cause / 根因
新版 edge-tts 只发送 SentenceBoundary 事件(不发 WordBoundary)。条件 chunk["type"] == "WordBoundary" 永远不成立 New edge-tts only emits SentenceBoundary chunks (not WordBoundary). The condition never matches
Fix / 修复
修改条件同时接受两种事件(voice.py 第1012行):Change condition to accept both (voice.py line 1012):
# Old:
elif chunk["type"] == "WordBoundary":
# New:
elif chunk["type"] in ("WordBoundary", "SentenceBoundary"):
🤖 LLM 与 API 配置🤖 LLM & API Configuration 2 bugs
Symptom / 症状
RetryProviderError: RetryProvider failed所有免费 GPT 供应商全部报错all free GPT providers return errors
Root Cause / 根因
免费 g4f 供应商不稳定/无人维护/被屏蔽;还缺依赖:curl_cffi, undetected_chromedriver, platformdirs Free g4f providers are unstable/unmaintained/blocked; missing deps: curl_cffi, undetected_chromedriver, platformdirs
Fix / 修复
切换到 Qwen(DashScope)——免费额度,国内直连。→ 完整替代方案:Qwen / Moonshot / DeepSeek / OpenAI 配置指南 Switch to Qwen (DashScope) — free quota, China direct. → Full alternatives guide: Qwen / Moonshot / DeepSeek / OpenAI config
Symptom / 症状
Error code: 429 - account suspended due to insufficient balance
Root Cause / 根因
Moonshot API Key 没有免费额度了Moonshot API key has no free credits left
Fix / 修复
注册阿里云百炼/DashScope:Register at Aliyun Bailian/DashScope:
https://dashscope.console.aliyun.com/
免费获取 API Key,百万 token 额度Get free API key with million-token quota
🖥️ 系统与 UX 陷阱🖥️ System & UX Traps 2 bugs
Symptom / 症状
OSError: [WinError 1455] The paging file is too small
Root Cause / 根因
moviepy 调起的 FFmpeg 需要的内存超过 Windows 虚拟内存池可用量 FFmpeg spawned by moviepy needs more memory than available in Windows virtual memory pool
Fix / 修复
1. 关闭不必要的程序。2. 杀掉残留 ffmpeg:1. Close unnecessary programs. 2. Kill stale ffmpeg:
taskkill /F /IM ffmpeg.exe
3. 如果仍然失败:设置 → 系统 → 关于 → 高级系统设置 → 性能 → 高级 → 虚拟内存 → 自定义:初始 4096,最大 8192 → 重启 3. If still fails: Settings → System → About → Advanced system settings → Performance → Advanced → Virtual memory → Custom: Initial 4096, Max 8192 → Restart
Symptom / 症状
Invalid voice ''TTS 失败3次后任务返回 None(Streamlit 报 AttributeError)TTS fails 3 times, then task returns None (AttributeError in Streamlit)
Root Cause / 根因
Streamlit 侧边栏未选择配音;voice_name 默认为空字符串 No voice selected in Streamlit sidebar; voice_name defaults to empty string
Fix / 修复
必须在 Speech Synthesis 下拉菜单中选择配音(例如 en-US-AnaNeural-Female Must select a voice from the Speech Synthesis dropdown (e.g. en-US-AnaNeural-Female)

📋 修改文件汇总📋 Summary: Files Modified

所有修改均在 app/services/ 目录下: All changes are in app/services/:

文件File修改内容Changes
voice.py5处修复:添加 mktimestamp、subs→cues、offset→cues[-1].end、create_sub→feed、WordBoundary→SentenceBoundary5 fixes: mktimestamp (add), subs→cues, offset→cues[-1].end, create_sub→feed, WordBoundary→SentenceBoundary
video.py2处修复:temp_audiofile_path→temp_audiofile,目录路径→文件路径2 fixes: temp_audiofile_path→temp_audiofile, directory→file path
config.tomlllm_provider=qwen,pexels_api_keys 填入llm_provider=qwen, pexels_api_keys filled

📌 可工作的依赖版本📌 Dependency Versions That Work

Package版本Version备注Note
moviepy1.0.3❌ 不要用 2.0.0+❌ NOT 2.0.0+
edge-tts最新版latest⚠️ 需要上述5个代码补丁⚠️ requires 5 code patches above
dashscope最新版latest✅ 兼容 Qwen/Bailian API Key✅ still compatible with Qwen/Bailian keys
🎯 诚实结论:MPT 可以工作——生成的视频效果不错,够用在无出镜内容频道上。但首次安装在国内网络环境下预计 2–4 小时,即使没有墙,也至少需要 30 分钟。官方文档一个字都没提这些坑。希望这份 Bug 目录能帮你省下这 4 小时。 🎯 Honest Verdict: MPT works — the output is decent enough for faceless content channels. But expect 2–4 hours of debugging on first install in China. Even without the GFW, it'd still take 30+ minutes. The official docs skip everything you just read. Hopefully this bug catalog saves you those 4 hours.

About MoneyPrinterTurbo

MoneyPrinterTurbo 由国内开发者 harry0703 创建并开源,是目前 GitHub 上最受欢迎的 AI 视频生成工具之一——截至 2026 年 5 月已获得 72,000+ Stars 和 10,000+ Forks,长期位列 GitHub Trending 前列。 MoneyPrinterTurbo was created and open-sourced by developer harry0703. It is one of the most popular AI video generation tools on GitHub — with 72,000+ stars and 10,000+ forks as of May 2026, consistently ranking on GitHub Trending.

项目采用 MIT 开源许可证——可自由商用、修改和分发,无任何限制。技术栈基于 Python,核心流水线整合了 LLM(文案生成)、TTS(配音)、Pexels(素材搜索)和 moviepy + FFmpeg(视频合成)。 Licensed under MIT — free for commercial use, modification, and redistribution with no restrictions. The tech stack is Python-based, integrating LLM (script generation), TTS (voiceover), Pexels (stock footage), and moviepy + FFmpeg (video composition).