harry0703/MoneyPrinterTurbo v1.3.7

on GitHub

English | 中文

Highlights

• Added word-by-word subtitles and a pop-up spring animation, with independent controls for display mode and animation in the WebUI.
• Added preset background music selection with in-browser audio preview, so you can listen before generating a video.
• Added native pauses to scripts with Azure TTS V1 (Edge TTS): use [pause: 2s] or [停顿: 2s] to insert silence while keeping narration and subtitles aligned.
• Added Kokoro and VoxCPM TTS providers. Kokoro supports a self-hosted OpenAI-compatible service and automatically loads the server's voice list.
• Added Claude Code as an LLM provider using an authenticated Claude subscription, with dedicated Docker deployment files; also added the OpenAI-compatible API Route provider.
• Improved Shengsuan Cloud video generation with account-specific model discovery, quotes and explicit cost confirmation, plus clip-count recommendations based on narration duration.
• Reduced repeated material selection across videos generated in the same task when using Pexels, Pixabay, Coverr, or local files. Material reuse is reported when the available pool is insufficient.
• Added a YouTube “Made for kids” audience setting to Upload-Post publishing.
• Added Azerbaijani WebUI localization and updated translations for the new settings and prompts.

Fixes and Improvements

• Improved subtitle animation rendering, including synchronized scaling of subtitle images and transparency masks to avoid black outlines when subtitles appear.
• Hardened Kokoro voice discovery and audio handling: retain the selected voice when the service is unavailable and validate generated audio before replacing existing files.
• Added pause-tag validation and improved multi-segment narration/subtitle synchronization; invalid speech chunks now stop generation rather than silently producing incomplete narration.
• Handled non-finite voice rates such as NaN and infinity more safely.
• Fixed the WebUI launch script's port check when the project path contains spaces, and corrected imports and repository paths in the Colab notebook.
• Added periodic log messages while FFmpeg concatenation is running, making long-running processing easier to diagnose.
• Extended material cache cleanup to reclaim temporary files left behind by interrupted writes.
• Updated the agent helper to support openai_image and recognize claude_code as a keyless LLM provider.
• Synced the documented Edge TTS voice list with the built-in catalog and clarified where to find the Windows one-click package in release Assets.

Usage and Upgrade Notes

• Subtitle defaults remain sentence display with no animation. Word-by-word timing works best with Azure TTS V1 (Edge TTS) or Whisper; providers without word-level timestamps may display phrases or whole sentences instead.
• Script pause tags are supported only with Azure TTS V1 (Edge TTS), with individual pauses from 0.1 to 10 seconds.
• Kokoro requires a separately running compatible TTS service. Claude Code requires its CLI and subscription authentication; selecting either provider does not install or authenticate the underlying service automatically.
• The YouTube audience setting is an explicit user declaration, not automatic content classification. It defaults to not made for kids; review the setting before uploading.
• Batch material allocation reduces reuse within a single task; it does not guarantee unique footage when there are too few source clips and does not change paid AI material providers' allocation behavior.

What's Changed

• Word-by-word subtitles and spring animation — @farhanahmad15 in #1313.
• Preset background music selection — @farhanahmad15 in #1314, followed by audio preview improvements.
• Claude Code subscription provider — @fred-ng in #1319.
• WebUI launcher support for paths containing spaces — @tailieu2212 in #1321.
• Kokoro TTS provider — @rocketlang in #1325.
• Shengsuan Cloud video workflow improvements — adapted from @huanglvjing's contribution in #1328, incorporated in 5ceffd0.
• Native script pauses — @IsmaelCamC in #1330.
• Non-finite voice rate handling — @Sushanth012 in #1333.
• Colab notebook fixes — @FrioNode in #1334.
• Azerbaijani WebUI translation — @jamalkamaladdin in #1339.
• Reduced batch material reuse — @giteePro in #1340.
• Edge TTS voice catalog documentation — @dajiaohuang in #1341.
• VoxCPM TTS provider — @lottshin in #1343.
• Orphaned material cache temporary-file cleanup — @c020627 in #1345.
• Release Assets download guidance — @c020627 in #1349.
• FFmpeg concatenation progress logging — @c020627 in #1351.
• Agent helper support for image generation and keyless Claude Code — @c020627 in #1352 and #1353.
• API Route LLM provider — @DennyHo0917 in #1354, with README updates by @c020627 in #1355.
• YouTube audience declaration — bfd7612.

Thanks to all contributors and everyone who reported issues and helped test these changes!

Full Changelog: v1.3.6...v1.3.7

重点更新

• 新增逐词字幕和弹跳出现动画，WebUI 可分别选择字幕显示模式与动画效果。
• 新增预设背景音乐选择与浏览器内试听，生成视频前即可确认配乐效果。
• 新增 Azure TTS V1（Edge TTS）脚本停顿支持：使用 [停顿: 2s] 或 [pause: 2s] 插入静音，并同步调整配音与字幕时间轴。
• 新增 Kokoro 和 VoxCPM 配音服务。Kokoro 支持自托管的 OpenAI 兼容服务，并自动读取服务端音色列表。
• 新增通过已认证 Claude 订阅使用的 Claude Code 大模型服务，提供专用 Docker 部署文件；同时新增 OpenAI 兼容的 API Route 大模型服务。
• 优化胜算云视频生成流程，支持读取当前账号可用模型、获取报价和确认费用，并根据旁白时长推荐素材数量。
• 减少同一任务批量生成多个视频时的素材重复，适用于 Pexels、Pixabay、Coverr 和本地文件；素材不足而发生复用时会给出提示。
• Upload-Post 新增 YouTube“是否面向儿童”受众设置。
• 新增阿塞拜疆语 WebUI 翻译，并补齐新设置与提示的多语言文案。

修复与改进

• 优化字幕动画渲染，同步缩放字幕画面与透明蒙版，避免字幕出现时产生黑色轮廓。
• 完善 Kokoro 音色读取与音频处理：服务暂时不可用时保留原有音色选择，替换文件前校验生成音频。
• 增加停顿标签校验，改进分段配音与字幕同步；无效语音片段会中止生成，避免静默输出缺失旁白的成片。
• 完善 NaN、无穷大等非有限语速值的处理。
• 修复项目路径包含空格时 WebUI 启动脚本的端口检查，并修正 Colab notebook 的缺失导入和仓库路径。
• FFmpeg 拼接期间增加定期日志，便于判断长时间处理状态和排查问题。
• 素材缓存清理支持回收写入中断后遗留的临时文件。
• Agent 辅助脚本新增 openai_image 支持，并正确识别无需 API Key 的 claude_code 服务。
• 将 Edge TTS 文档音色列表与内置音色库同步，并明确 Windows 一键包在 Release Assets 中的下载位置。

使用与升级说明

• 字幕默认仍为按句显示、无动画。逐词时间轴在 Azure TTS V1（Edge TTS）或 Whisper 下最准确；其他服务缺少逐词时间戳时，可能按短语或整句显示。
• 脚本停顿标签仅支持 Azure TTS V1（Edge TTS），单次停顿范围为 0.1～10 秒。
• Kokoro 需要单独运行兼容的配音服务；Claude Code 需要安装 CLI 并完成订阅认证。选择服务商不会自动完成底层服务的安装或认证。
• YouTube 受众设置由用户主动声明，不会自动识别视频内容。默认非面向儿童，上传前请根据实际内容确认。
• 批量素材分配仅减少同一任务内的重复；素材不足时仍可能复用，不保证每条视频的画面完全不同，也不改变付费 AI 素材服务的分配行为。

主要变更

• #1313：逐词字幕与弹跳动画，感谢 @farhanahmad15。
• #1314：预设背景音乐选择，感谢 @farhanahmad15；后续补充了音乐试听。
• #1319：Claude Code 订阅大模型服务，感谢 @fred-ng。
• #1321：修复含空格路径下的 WebUI 启动检查，感谢 @tailieu2212。
• #1325：Kokoro 配音服务，感谢 @rocketlang。
• #1328：吸收并优化胜算云视频生成流程，感谢 @huanglvjing，已通过 5ceffd0 纳入。
• #1330：脚本原生停顿支持，感谢 @IsmaelCamC。
• #1333：非有限语速值处理，感谢 @Sushanth012。
• #1334：修复 Colab notebook，感谢 @FrioNode。
• #1339：阿塞拜疆语 WebUI 翻译，感谢 @jamalkamaladdin。
• #1340：减少批量视频素材重复，感谢 @giteePro。
• #1341：同步 Edge TTS 音色文档，感谢 @dajiaohuang。
• #1343：VoxCPM 配音服务，感谢 @lottshin。
• #1345：清理素材缓存遗留临时文件，感谢 @c020627。
• #1349：完善 Release Assets 下载指引，感谢 @c020627。
• #1351：FFmpeg 拼接进度日志，感谢 @c020627。
• #1352、#1353：Agent 辅助脚本支持文生图与免 API Key 的 Claude Code，感谢 @c020627。
• #1354：API Route 大模型服务，感谢 @DennyHo0917；#1355 补齐 README 说明，感谢 @c020627。
• bfd7612：YouTube 受众声明设置。

感谢所有贡献代码、反馈问题和参与测试的朋友！

完整变更记录：v1.3.6...v1.3.7