Skip to content
cccskills
FreePublished on GitHub

ai-voiceover-edge-tts

AI 口播配音:用免费的 edge-tts(微软 Edge 在线语音)为带货短视频逐句生成配音,自动去首尾静音、统计每句时长、缓存复用,可选音色/语速/音调,并给出口播稿改写规则。

Use when the user needs a voice-over, 配音, 口播, 旁白, TTS, text-to-speech, AI 主播声音, or wants to turn a script into audio for 抖音 / TikTok / 视频号 videos.

The English summary is being prepared. Showing the original description.

Works withTikTok

Run score Not tested

See how to install

Files included (2)

  • SKILL.md4.0 KB
  • scripts/tts_edge.py4.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

AI 口播配音 · Voice-over with edge-tts

逐句合成 → 去静音 → 48 kHz WAV → durations.json。后续的字幕、镜头时长都按真实配音时长对齐,不再「声画对不上」。

Part of ecommerce-video-skills · 脚本:scripts/tts_edge.py(仅依赖 edge-tts + ffmpeg)

输入 Inputs

  • 口播稿(一句一行,或 storyboard.json 的 line 字段)
  • 语言 / 音色偏好(男/女、活泼/沉稳)、语速
  • 环境:pip install edge-tts,ffmpeg,能访问微软 TTS 服务的网络

步骤 Steps

  1. 改写成「好读」的口播稿(见规则),每句 8–20 字。

  2. 选音色(python scripts/tts_edge.py --list zh-CN 查看全部):

    场景推荐音色
    活力种草(男)zh-CN-YunxiNeural
    亲切种草(女)zh-CN-XiaoxiaoNeural / zh-CN-XiaoyiNeural
    激情促销zh-CN-YunjianNeural
    专业讲解zh-CN-YunyangNeural
    台湾 / 香港zh-TW-HsiaoChenNeural / zh-HK-HiuMaanNeural
    Englishen-US-AndrewNeural · en-US-AvaNeural · en-US-EmmaNeural
  3. 合成:

    pip install edge-tts
    # 单句试听
    python scripts/tts_edge.py "夏天带冰水出门,不到中午就变温了?" --voice zh-CN-YunxiNeural --rate "+10%" -o out/hook.wav
    # 整个分镜(每镜一句 → build/tts/l00.wav … + durations.json)
    python scripts/tts_edge.py --storyboard storyboard.json --outdir build/tts
    
  4. 试听 2 句再批量:语速 +5%~+15% 最像带货口播;超过 +20% 会显得赶。

  5. 交给 ffmpeg-auto-assemble(它会自动调用本脚本)或自己的剪辑软件。

口播稿改写规则 Script rules

  • 数字写成「读法」:2核8G → 两核八G;24h → 二十四小时;型号字母之间加空格 A I。字幕可以保留原写法(sub 字段)。
  • 一句只说一件事;逗号就是换气点,句末用句号/问号让语调落下来。
  • 去掉书面词:「此款产品具有…」→「这只杯子…」。
  • 英文品牌名若读错,用拼读或谐音写进 line,sub 保留正确拼写。

提示词模板 Prompt template

把下面的带货文案改写成适合 TTS 朗读的口播稿:每句 8–20 字、一句一件事、口语化;
数字和字母写成读法;另外输出一列「字幕版」保留原始写法并用 **加粗** 标 1 个关键词。
不要添加原文没有的卖点或数据。原文:{…}

检查清单 Checklist

  • 先试听 2 句确认音色/语速
  • 数字、英文、品牌名读音正确
  • durations.json 已生成,总时长符合目标
  • 商用前确认所在平台与地区对 AI 配音的标注要求(如需标注「AI 生成」)

常见问题与修复 Failure fixes

问题修复
edge-tts failed / 超时网络问题,脚本已重试 3 次;换网络或稍后再试;离线时用 assemble.py --tts none 先预览画面
读音错误在 line 里写谐音/拼读,sub 保留原文
句子之间停顿太长已自动去首尾静音;调 storyboard 的 pad(默认 0.25s)
声音太平换 YunjianNeural/XiaoyiNeural;--pitch "+5Hz";句尾用问号/感叹号
需要真人感edge-tts 是合成音;高要求场景改用真人录音,流水线照样可用(把录音放进 build/tts/lXX.wav)

edge-tts 由社区维护(rany2/edge-tts,LGPL-3.0),调用的是微软在线服务;本仓库只把它当依赖安装,不包含其代码。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

封面与标题 A/B:为带货短视频生成多套封面(自动挑选清晰帧或用干净素材图 + 不同标题与版式)和多组标题/文案,导出 3:4 / 9:16 封面文件和对比图,并给出 A/B 测试方法与记录表。Use when the user wants a video cover, 封面, 首图, thumbnail, 标题, 文案, title variants, A/B test covers for 抖音 / 视频号 / 小红书 / TikTok, or wants to improve click-through rate.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

ffmpeg 自动拼接成片:一条命令把 storyboard.json(商品图/视频片段 + 口播稿)渲染成带配音、字幕花字、转场、BGM 自动闪避、响度标准化的 9:16 MP4,纯本地运行。Use when the user wants to assemble/edit/render a product video, 自动剪辑, 一键成片, 拼接视频, 图片转视频, Ken Burns, add BGM/subtitles/voice-over with ffmpeg, or batch-produce short videos without an editor.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

3 秒钩子脚本:为电商短视频写前 3 秒开场(台词 + 画面 + 花字),按痛点/反差/结果先行/提问/数字/场景代入等钩子类型一次给出多版,并做合规自检。Use when the user asks for a hook, 开头, 黄金 3 秒, 前三秒, opening line, scroll-stopper, 完播率, or wants to rewrite a weak opening for 抖音 / TikTok Shop / 视频号 / Reels.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

主图转视频:把一张或几张商品主图/白底图/场景图,写成可直接喂给图生视频模型的镜头提示词(运镜、主体动作、光线、时长、负面约束),并保证商品不变形。Use when the user has product images and wants a product video, 主图视频, 图生视频, image-to-video, animate a product photo, or 让主图动起来 — with any image-to-video model (Seedance / 可灵 Kling / Veo / Runway / Hailuo / Wan …) or a local Ken Burns fallback.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

直播切片:从电商直播录屏中找出高光片段(按时间戳 / 按字幕关键词 / 按停顿自动提议),批量导出 9:16 竖屏切片,自动模糊填充横屏画面、烧录标题与字幕、响度标准化,并给切片写标题与开头钩子。Use when the user has a livestream recording and wants 直播切片, 切片, highlights, clips, 高光片段, repurpose a live stream into short videos for 抖音 / 视频号 / TikTok.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

多模型镜头提示词适配:把一份分镜表改写成适合不同视频生成模型的提示词(中/英、首帧/首尾帧/纯文生视频、运镜词表、负面约束),模型中立、不编造价格或参数。Use when the user wants the same shot list adapted for Seedance, 可灵 Kling, Veo, Runway, Hailuo/海螺, Wan/通义万相, Sora, Pika or 'any video model', asks 怎么写视频提示词, camera movement terms, or a model returns deformed products.

The English summary is being prepared. Showing the original description.

xianyu110/ecommerce-video-skills97Updated Oct 5, 2026

See all skills by xianyu110

Report a problem with this skill