agentmods.dev

minimax-voice-director

minimax-voice-director is a skill for Codex from bozhouDev/video-skills-toolkit. It costs 99 tokens per session (1,415 once invoked), scanned A, original, MIT.

A skill for directing, generating, reviewing, and approving MiniMax voice recordings for video narration before producing subtitles from the final audio.

In plain words
What is it for?
It helps prepare pronunciation and performance instructions, generate voice takes after approval, choose and approve audio, and create subtitles from the approved recording.
Why use it?
It adds review and approval stages so voice direction and selected recordings can be checked before cloud generation or further processing.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 159repo +4 3mo ago A scan SkillSpector: pass 99 tokens original MIT

Good fit It helps prepare pronunciation and performance instructions, generate voice takes after approval, choose and approve audio, and create subtitles from the approved recording.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bozhoudev/video-skills-toolkit/minimax-voice-director
View source ↗ bozhouDev/video-skills-toolkit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add bozhouDev/video-skills-toolkit --skill minimax-voice-director
Clone the repo
git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for minimax-voice-director

README.md
[![agentmods](https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/minimax-voice-director/github.svg)](https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/minimax-voice-director)
Your own site
<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/minimax-voice-director"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/minimax-voice-director/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for minimax-voice-director

Your own site · 80×15
<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/minimax-voice-director"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/minimax-voice-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00099 $0.01415
Opus 5.5 $0.00040 $0.00566
Sonnet 5.5 $0.00020 $0.00283
Haiku 4.5 $0.00010 $0.00142

Measured 2mo ago against content hash 43369d32b0d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

minimax-voice-director scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 15 executable files (assets/minimax_tts.py, scripts/approve_audio.py, scripts/approve_direction.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/minimax-voice-director/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax 声音导演

把口播稿变成可审批、可复现、可局部返工的声音表演。不得把本 skill 缩减为“文本进、MP3 出”的单次 TTS 调用。

路由边界

  • 用户明确选择 MiniMax 配音，或当前项目已经用 MiniMax：进入三阶段主流程。
  • 用户只说 TTS、旁白、自己的声音，但没有选 MiniMax：不自动替换引擎，先根据上下文路由到合适的本地或云端工作流。
  • 用户要 MiniMax Voice ID、声音克隆、声音设计或旧函数兼容：读 references/runtime.md，该分支不自动触发配音主流程。
  • 音乐、BGM、歌曲或 cover：改用同级 music（ElevenLabs Music API）。
  • 不因其他 TTS 失败而静默转用 MiniMax；先说明云端费用、声音差异和数据上传。

三阶段主流程

1. 先导演，再审批

  1. 定义原稿和字幕文本真值，先处理产品名、人名、数字、缩写和多音字。
  2. 读 references/directing.md 设计全片基线、言语动作、潜台词、情绪弧线、节奏曲线、焦点词、语调和必要的声音事件。
  3. 读 references/schema.md，从 assets/voice-direction.template.yaml 创建 work/tts/voice-direction.yaml。平台私有标签不得出现在导演中间层。
  4. 运行 scripts/validate_direction.py 和 scripts/compile_direction.py，产生审查视图、lint、MiniMax manifest 和干净字幕稿。
  5. 用独立审查回合检查导演逻辑，重点展示改写、强焦点、强转折、长停顿、声音事件、局部参数和多 Take 段落；通过后运行 scripts/mark_reviewed.py 固化审查 hash。
  6. 停在这里等待用户批准。 用户没有明确批准时，不得运行 approve_direction.py，不得调用 MiniMax。
  7. 用户批准后运行 scripts/approve_direction.py，再重新编译。render_allowed 必须为 true。

2. 生成、选 Take，再批准音频

  1. 读 references/workflow.md 和 references/runtime.md，加载项目 .env.r2，不输出任何密钥或 Voice ID。
  2. 运行 scripts/render_segments.py。它必须同时验证人工批准、lint 和内容 hash；任一失效就拒绝云端生成。
  3. 正式生成优先使用长连续块：开头约 40 秒一块，后续约 3 分钟一块；时长只是软目标，必须在句号或完整意群结尾切分，绝不从句子中间硬截。每块默认 1 个 Take，局部问题只重生局部。
  4. 听审候选并写入 take-selection.yaml，然后运行 scripts/select_takes.py 和 scripts/finalize_voice.py。不得把原始候选或未重建停顿的拼接音频冒充最终成果。
  5. 在最终速度下验收开头 15 秒、一个中段、所有主要转折和收尾；检查发音、节奏、焦点、情绪连续性、音色漂移和声音标签执行。
  6. 再次停下等待用户批准最终音频。 获得批准后运行 scripts/approve_audio.py 和 scripts/publish_voice.py。

3. 只从定稿音频生成字幕

  1. 只对 audio_approved 且 hash 匹配的最终 WAV 生成时间轴；M4A/MP3 是发布衍生物，不作为字幕时间基准。任何 Take、速度、裁剪或拼接变化都使旧时间轴失效。
  2. 使用 audio-to-subtitles 生成 ASR 时间轴。该步骤需要 R2/MediaKit 凭证并会上传最终音频；使用项目已授权凭证，不打印密钥。
  3. ASR 只提供时间轴。用 work/tts/subtitle-source.txt 回填最终显示文本，不显示呼吸、停顿和发音标记。
  4. 读 references/output-layout.md 交付 SRT/VTT/JSON 和 raw ASR 证据，通过 scripts/mark_subtitled.py 把交付文件的 hash 绑定到已批准音频。数字人、口型和正式剪辑都必须以这份定稿音频为唯一时间基准。

引擎能力边界

导演稿使用 sound tags、局部参数或要求重音/语调控制时，读 references/capabilities.md。每个导演意图必须被标识为：

Read the full file on GitHub · 67 lines

Files

What ships with it

23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 67 lines · 99 tokens per session scan A 43369d32b0d5

Subscribe to this mod's changes

minimax-voice-director is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (159 stars, last pushed 3mo ago), licensed MIT. It adds 99 tokens to every session and 1,415 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and mediaai-skillsremotionsubtitlesttsvideo
Related

minimax-voice-director compared with skills from other repositories

minimax-voice-director next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
minimax-voice-directorbozhouDev/video-skills-toolkitSkill1593mo agoMITA99Codex
video-strategy-orchestratoroyi77/1ai-skillsSkill17yesterdayMITA96Claude Code
video-transcriberellmos-ai/skillsSkill94d agoMITA48Claude Code, Codex
video-hyperframesnexu-io/open-designSkill106kyesterdayApache-2.0A18Claude Code, Codex
videoRemocn/remocnSkill1.7kyesterdayMITA96Claude Code
studioRemocn/remocnSkill1.7kyesterdayMITA72Claude Code
video-hyperframesnexu-io/html-anythingSkill9.4k24d agoApache-2.0A22Claude Code, Codex