AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Aliang Podcast Maker

skill-aliang2052-aliang-skills-aliang-podcast-maker · by aliang2052

多人对话脚本转语音播客:为不同角色分配音色,逐句生成后用 ffmpeg 拼接成完整音频。

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-aliang2052-aliang-skills-aliang-podcast-maker

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-aliang2052-aliang-skills-aliang-podcast-maker)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Aliang Podcast Maker? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

多人对话播客制作 Skill

触发词

当用户提供多角色对话脚本、播客剧本、访谈内容,并要求"做成声音"、"制作播客"、"配音"时使用。

工作流

第一步:分析对话,分配音色

  1. 识别对话中的角色数量和各自特点(性格、年龄、语气)
  2. 列出可用音色:
bl speech synthesize --list-voices --model cosyvoice-v3-flash
  1. 为每个角色匹配合适的音色:

| 角色类型 | 推荐音色 | 说明 | |----------|---------|------| | 活泼女性 | longanhuan | 欢脱元气女 | | 沉稳女性 | longxiaoxia_v3 | 沉稳权威女 | | 知性女性 | longanwen_v3 | 优雅知性女 | | 磁性男性 | longtian_v3 | 磁性理智男 | | 温暖男性 | longze_v3 | 温暖元气男 | | 青年男性 | longcheng_v3 | 智慧青年男 |

  1. 向用户展示音色方案,确认后继续。

第二步:逐句生成语音

创建临时目录存放分句音频:

mkdir -p {输出目录}/{对话标题}_语音

按对话顺序,为每句生成音频。阿琳用 longanhuan、老陈用 longtian_v3 举例:

# 阿琳第1句
bl speech synthesize \
  --text "好了,咱今天就唠唠——AI 这么猛,到底还需要什么样的人才?" \
  --voice longanhuan \
  --out "{输出目录}/{对话标题}_语音/阿琳_01.mp3"

# 老陈第1句
bl speech synthesize \
  --text "我觉得是 T 字型的人。" \
  --voice longtian_v3 \
  --out "{输出目录}/{对话标题}_语音/老陈_01.mp3"

继续为所有对话逐句生成。命名格式:{角色名}_{序号}.mp3

注意:

  • 使用 --model cosyvoice-v3-flash(系统音色默认,可不写)
  • 如需调整语速/语调,添加 --rate / --pitch 参数

第三步:创建 ffmpeg 拼接列表

在语音目录下创建 concat_list.txt,按对话顺序排列:

file '阿琳_01.mp3'
file '老陈_01.mp3'
file '阿琳_02.mp3'
file '老陈_02.mp3'
...

第四步:拼接为完整音频

关键发现:Bailian TTS 虽然输出 .mp3 扩展名,实际格式是 WAV(PCM)。 因此拼接时必须转码:

ffmpeg -y -f concat -safe 0 -i {输出目录}/{对话标题}_语音/concat_list.txt \
  -c:a libmp3lame -b:a 192k \
  {输出目录}/{对话标题}_完整版.mp3
  • -y:自动覆盖已存在文件
  • -c:a libmp3lame:转码为真 MP3
  • -b:a 192k:192kbps 音质

第五步:清理与报告

  1. 删除临时 concat_list.txt
  2. 向用户报告:
  • 完整音频路径和时长
  • 分句音频目录位置
  • 使用的音色方案

输出示例

✅ 播客制作完成!

完整音频:输出/T型人才对话_完整版.mp3
  - 时长:68秒
  - 格式:MP3, 192kbps, 24kHz
  - 大小:1.3MB

音色方案:
  阿琳 → longanhuan(欢脱元气女)
  老陈 → longtian_v3(磁性理智男)

分句音频:输出/T型人才对话_语音/(13个文件)

进阶:添加片头/片尾音效

如果需要添加背景音乐或音效:

# 片头音频 + 完整对话拼接
ffmpeg -y -f concat -safe 0 \
  -i 20句),可并行生成以提高效率
- 使用 `cosyvoice-v3.5-flash` 模型时(克隆音色),命令中的 `--model` 参数必须显式指定

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [aliang2052](https://github.com/aliang2052)
- **Source:** [aliang2052/aliang-skills](https://github.com/aliang2052/aliang-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.