Audio To Subtitles

What it does

When your agent uses it

• The user asks to turn audio/video into subtitles
• Generate ASR subtitles
• Batch transcription
• Generate TTS audio with optional subtitles

Example prompts

• “/audio-to-subtitles”

Requirements

• Node.js
• A credential in MINIMAX_API_KEY
• A credential in MINIMAX_TTS_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1If the input is a local file, upload it to Cloudflare R2 first.
2. 2Submit the public audio_url or video_url to AI MediaKit ASR subtitles.
3. 3Poll the async task until it is completed or failed.
4. 4Save .json, .srt, and .vtt outputs.

What it can do on your machine

Read from SKILL.md and the folder at commit 4766a16. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (TypeScript), which the agent can run.

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.minimax.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • MINIMAX_API_KEY
  • MINIMAX_TTS_API_KEY
  • MEDIAKIT_API_KEY
  • AI_MEDIAKIT_API_KEY
  • VOLCENGINE_MEDIAKIT_API_KEY
  • R2_ACCESS_KEY_ID
  • R2_SECRET_ACCESS_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audio To Subtitles loads about 1.9k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 657 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~153

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:113

  onment files in this order. The nearest `.env.r2` is loaded last and overrides global R2 defaults for this vault.

• NoteMentions a .env fileSKILL.md:115

  1. `~/.skills/.env`

• NoteMentions a .env fileSKILL.md:116

  2. `~/.baoyu-skills/.env`

• NoteMentions a .env fileSKILL.md:117

  3. nearest `.env.r2` from current directory upward

• NoteMentions a .env fileSKILL.md:118

  4. nearest `.skills/.env` from current directory upward

• NoteMentions a .env fileSKILL.md:119

  5. nearest `.baoyu-skills/.env` from current directory upward

• NoteMentions a .env fileSKILL.md:157

  - Do not print API keys or commit real `.env.r2` values.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from bozhouDev/video-skills-toolkit at commit 4766a16, republished under its MIT licence (© bozhouDev). 657 words, ~1,892 tokens.

name

audio-to-subtitles

description

Convert local audio/video files or public media URLs into subtitle files by uploading local files to Cloudflare R2 and calling Volcengine AI MediaKit ASR subtitles API. Also supports MiniMax text-to-speech generation from text or text files, with optional subtitle generation from the produced audio. Supports batch processing, SRT/VTT/JSON output, language selection, speaker labels, configurable MiniMax voice ID and model. Use when the user asks to turn audio/video into subtitles, generate ASR subtitles, create SRT/VTT, batch transcription, or generate TTS audio with optional subtitles.

<VIDEO_WORKSPACE>/<project>/work/captions

# Set this to the directory containing this installed skill (not the current working directory).
SKILL_DIR="<SKILL_ROOT>/audio-to-subtitles"

# Local audio/video: upload to R2, then transcribe
npx -y bun "$SKILL_DIR/scripts/main.ts" audio.mp3 --language zh-CN --out-dir subtitles

# Existing public URL: skip R2 upload
npx -y bun "$SKILL_DIR/scripts/main.ts" "https://example.com/audio.mp3" --out-dir subtitles

# Batch files/URLs
npx -y bun "$SKILL_DIR/scripts/main.ts" a.mp3 b.m4a "https://example.com/video.mp4" --out-dir subtitles

# Batch from manifest
npx -y bun "$SKILL_DIR/scripts/main.ts" --manifest inputs.txt --out-dir subtitles

# Speaker diarization
npx -y bun "$SKILL_DIR/scripts/main.ts" interview.mp3 --speaker --language zh-CN

# Text to audio only
npx -y bun "$SKILL_DIR/scripts/main.ts" --text "你好，欢迎收听。" --voice-id female-shaonv --out-dir audio

# Text file to audio + subtitles
npx -y bun "$SKILL_DIR/scripts/main.ts" --text-file script.md --subtitles --language zh-CN --out-dir audio

[
  "local-audio.mp3",
  { "url": "https://example.com/video.mp4", "mediaKind": "video" },
  { "text": "你好，欢迎收听。", "outputName": "intro", "subtitles": true, "voiceId": "female-shaonv" },
  { "textFile": "script.md", "outputName": "script-audio", "subtitles": true }
]

© bozhouDev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in skills/audio-to-subtitles of bozhouDev/video-skills-toolkit.

• SKILL.md
• scripts/main.ts
• scripts/r2.ts

Open the folder on GitHubat commit 4766a16