Media To Transcript

What it does

When your agent uses it

• The user asks for 逐字稿
• Wants a polished transcript

Example prompts

• “提取视频文案”
• “/media-to-transcript”

Requirements

• Python 3
• A credential in VOLCENGINE_SPEECH_API_KEY
• A credential in VOLCENGINE_AUC_API_KEY

Workflow steps

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

1. 1Run the doctor if this is the first run, after environment changes, or after an error
2. 2Run the pipeline from the notes vault root

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 1 file in scripts/ (Python), which the agent can run.

  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:

  • openspeech.bytedance.com
  • bilibili.com

  Also links to:

  • console.volcengine.com

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

• Credentials

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

  • VOLCENGINE_SPEECH_API_KEY
  • VOLCENGINE_AUC_API_KEY
  • SEEDASR_API_KEY
  • AUC_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

Media To Transcript loads about 1.8k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 145 tokens; SKILL.md has 614 words of instructions outside code blocks.

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

~145

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

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.4k

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:103

  key location is your current workspace `.env.r2`, or any environment file loaded by the script:

• NoteMentions a .env fileSKILL.md:120

  3. Put the key into your workspace `.env.r2` as `VOLCENGINE_SPEECH_API_KEY=...`, or export it in the shell before runnin

• NoteMentions a .env fileSKILL.md:130

  Do not print API keys or copy `.env.r2` values into chat.

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). 614 words, ~1,776 tokens.

name

media-to-transcript

description

Convert audio/video URLs or local media into corrected Markdown transcripts through Volcengine recording-file ASR 2.0. Reuses the existing video-transcript downloader for Bilibili, Douyin, Xiaohongshu, YouTube, extracts audio when input is video, uploads local audio to R2, splits media longer than 3 minutes into parallel AUC tasks, submits volc.seedasr.auc with compact source context, then performs AI correction with topic/context/glossary. Use when the user asks for "逐字稿", "提取逐字稿", "视频转文字", "音频转文字", "转写", "听写视频", "提取视频文案", or wants a polished transcript.

SKILL_DIR="<SKILL_ROOT>/media-to-transcript"
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" --doctor

SKILL_DIR="<SKILL_ROOT>/media-to-transcript"
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "<URL或本地媒体路径>" --topic "视频主题或关键词" --language zh-CN

SKILL_DIR="<SKILL_ROOT>/media-to-transcript"

# Video URL: download video, extract mp3, upload to R2, then run AUC ASR
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "https://www.bilibili.com/video/BVxxx" --topic "AI 编程工具评测"

# Local audio/video
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" "/path/to/audio.mp3" --media-kind audio --topic "访谈"

# Add context or terminology hints for ASR and correction
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" video.mp4 \
  --topic "Claude Code 和 Codex 使用经验" \
  --context "技术词: Codex, Claude Code, MCP, HyperFrames, R2" \
  --context-file "AI Wiki/raw/some-material.md"

# Enable Volcengine utterance emotion labels when explicitly useful
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" video.mp4 --emotion --topic "访谈"

# Convert an existing AUC result JSON into raw transcript + correction prompt
rtk python3 "$SKILL_DIR/scripts/media_to_transcript.py" --from-asr-json asr/auc-result.json --title "视频标题"

VOLCENGINE_SPEECH_API_KEY=你的新版控制台APIKey

© 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 5 other files (scripts, references) in skills/media-to-transcript of bozhouDev/video-skills-toolkit.

• SKILL.md
• .gitignore
• README.md
• agents/openai.yaml
• references/correction-guidelines.md
• scripts/media_to_transcript.py

Open the folder on GitHubat commit 4766a16