New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audio Transcribe

by iurysza in iurysza/module-graph

Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps.

MITAuto-check passedMedia & Creative

Install Audio Transcribe

skills CLI
$ npx skills add iurysza/module-graph --skill audio-transcribe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install iurysza/module-graph audio-transcribe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/iurysza/module-graph.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audio-transcribe .claude/skills/audio-transcribe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audio-transcribe
GitHub stars
420
Token cost
~1k tokens
SKILL.md length
521 words
Files
4 (incl. scripts)
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps.

  • Works in 5 steps: Confirm the input exists and uses a… → Use ffprobe to inspect duration. → Agree on an output path when the user… → …
  • Similar recordings
  • SKILL.md covers Setup, Before transcription, Run and Output, plus 1 more section
  • Runs TypeScript scripts from its folder; calls bun; needs GOOGLE_API_KEY and OPENCODE_GOOGLE_API_KEY

What it does

Audio Transcribe is an agent skill from iurysza/module-graph. Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps. Use for interviews, meetings, lectures, podcasts, voice notes, and similar recordings.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/package.json`, `scripts/transcribe.test.ts` and `scripts/transcribe.ts`). Compatibility notes: Requires Bun 1.1+, ffmpeg/ffprobe, network access, and a Gemini API key.

It sits in Media & Creative, covering Transcription. The repository describes itself as: A Gradle Plugin for visualizing your project's structure, powered by mermaidjs. The licence is MIT.

When your agent uses it

  • Similar recordings
  • Tasks that involve Transcription

Example prompts

  • “Use the audio-transcribe skill to transcribe local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps”
  • “/audio-transcribe”

Requirements

  • Node.js
  • A credential in GEMINI_API_KEY
  • A credential in GOOGLE_API_KEY
  • Compatibility (from SKILL.md): Requires Bun 1.1+, ffmpeg/ffprobe, network access, and a Gemini API key.

Workflow steps

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

  1. Confirm the input exists and uses a supported format.
  2. Use ffprobe to inspect duration.
  3. Agree on an output path when the user does not provide one.
  4. Warn before an unexpectedly long or costly transcription.
  5. Ask for language hints and domain terms when they are known and likely to improve recognition.

What it can do on your machine

Read from SKILL.md and the folder at commit 15b0135. 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 3 files in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • bun

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

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

    • GOOGLE_API_KEY
    • OPENCODE_GOOGLE_API_KEY
    • GEMINI_API_KEY

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

  • Compatibility

    Requires Bun 1.1+, ffmpeg/ffprobe, network access, and a Gemini API key.

    From compatibility in the SKILL.md frontmatter.

Context cost

Audio Transcribe loads about 1k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 iurysza/module-graph at commit 15b0135, republished under its MIT licence (© iurysza). 521 words, ~1,046 tokens.

Download SKILL.mdSave it as .claude/skills/audio-transcribe/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
audio-transcribe
description
Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps. Use for interviews, meetings, lectures, podcasts, voice notes, and similar recordings.
compatibility
Requires Bun 1.1+, ffmpeg/ffprobe, network access, and a Gemini API key.
metadata.category
visual-media

Audio Transcription

The bundled CLI normalizes audio, uploads each chunk to Gemini 3.5 Transcribe, and writes one Markdown transcript. Default output uses Gemini's speaker diarization and word-level timestamps.

Setup

Resolve paths relative to this SKILL.md. Do not assume a global skill directory.

bash
bun install --cwd <skill-directory>/scripts --no-save
export GEMINI_API_KEY='...'

GOOGLE_API_KEY and OPENCODE_GOOGLE_API_KEY are fallbacks. Set GEMINI_TRANSCRIBE_MODEL only to select a compatible replacement model. The default is gemini-3.5-transcribe.

Before transcription

  1. Confirm the input exists and uses a supported format.
  2. Use ffprobe to inspect duration.
  3. Agree on an output path when the user does not provide one.
  4. Warn before an unexpectedly long or costly transcription.
  5. Ask for language hints and domain terms when they are known and likely to improve recognition.

Do not upload media without the user's explicit transcription request.

Run

bash
bun run <skill-directory>/scripts/transcribe.ts \
  ./interview.m4a \
  --language en-US \
  --vocabulary "SumUp" \
  --output ./interview-transcript.md

Options:

  • --chunk-minutes N: chunk duration. The default is 30.
  • --language CODE: BCP-47 language hint. Repeat the option for each known language. Omit it for automatic language detection and code-switching.
  • --vocabulary TERM: domain term, acronym, or proper name. Repeat the option for each term. Use it with --smart. Gemini accepts up to 1,000 terms. It normally performs best with a short, targeted list.
  • --smart: return a cleaned transcript. This removes filler words, repetitions, and false starts, but Gemini does not provide speaker labels or timestamps in this mode.
  • --output PATH: exact Markdown output path.
  • --keep: retain normalized audio and chunk files beside the transcript.
  • --help: show usage.

Default verbatim mode requests speaker diarization and word timestamps. Gemini limits those requests to 30 minutes of audio per request, so the CLI splits longer recordings. The live API rejects custom vocabulary with word timestamps, so the CLI fails clearly when --vocabulary is used without --smart. --smart supports chunks up to 60 minutes because it does not request either feature. If Gemini returns a rate-limit delay, the CLI waits for that delay and retries the interaction once.

Supported inputs: MP3, WAV, M4A, OGG, FLAC, and WebM.

Show full SKILL.md (201 more words)Show less

Output

Default output contains source metadata, duration, model, mode, language hints, custom vocabulary, chunk count, speaker-labelled turns, and timestamps from Gemini's word annotations. The CLI orders annotations by their audio timestamps before it formats turns. The CLI deletes each remote Gemini upload after its transcription request. It warns if that deletion fails.

--smart produces clean text from interaction.output_text. It does not invent timestamps or speaker identity that the API did not return.

Speaker labels identify distinct voices within one Gemini request, not verified people. The CLI adds a heading for each chunk because Gemini can reset labels after a split. Preserve labels such as Speaker 1 when names are uncertain. Do not present inferred identities as facts.

Verification

After transcription:

  1. Confirm that the command succeeded.
  2. Confirm that the Markdown file exists and is non-empty.
  3. Inspect the beginning, one middle section, and the end for missing chunks, speaker changes, or malformed timestamps.
  4. Report the exact path and disclose failed or partial processing.

The CLI does not write a transcript after a failed API request. It removes local normalized audio unless --keep is set. Never print API keys or add private media and generated transcripts to the skill repository.

© iurysza, 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 3 other files (scripts) in .agents/skills/audio-transcribe of iurysza/module-graph.

  • SKILL.md
  • scripts/package.json
  • scripts/transcribe.test.ts
  • scripts/transcribe.ts

Open the folder on GitHubat commit 15b0135

Compare with similar skills

Audio Transcribe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audio Transcribe compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audio Transcribe this skilliurysza/module-graph420—~1kAutomated safety check: PassMIT
HyperFrames Media Useheygen-com/hyperframes60k—~2.4kAutomated safety check: PassApache-2.0
Native Subtitle Quote Imagechengyi-ai/native-subtitle-quote-image2.6k—~1.8kAutomated safety check: PassMIT
Edu Chem Videowy51ai/edulab1.4k—~2.1kAutomated safety check: NotesApache-2.0
Transcription Memory ReconstructionNxcoreAI/EverRoom3k—~714Automated safety check: PassCustom licence
Edu Math Videowy51ai/edulab1.4k—~2.5kAutomated safety check: NotesApache-2.0

Similar skills

  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed

  • Native Subtitle Quote Image

    chengyi-ai/native-subtitle-quote-image

    将本地视频或用户有权处理的在线视频，经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、拼图和逐张质检，制作成 3:4 或保留画面原比例的视频字幕长图。支持两种明确分开的输出：保留画面内已烧录字幕的原生字幕模式，以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube…

    2.6k GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-check passed

  • Edu Chem Video

    wy51ai/edulab

    A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a chemistry problem (化学题: 氧化还原配平 双线桥 电子守恒, 物质的量计算, 化学平衡 三段式 平衡常数 转化率 反应速率, 离子反应, 电化学, 溶液 滴定…

    1.4k GitHub stars~2.1k tokensUpdated today
    Media & CreativeAuto-check: notes

  • Transcription Memory Reconstruction

    NxcoreAI/EverRoom

    Reconstruct a complete, searchable memory from an untrusted meeting or conversation transcript.

    3k GitHub stars~714 tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Edu Math Video

    wy51ai/edulab

    A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a math problem (数学题, geometry, algebra, functions, motion/行程 problems), from a problem screenshot…

    1.4k GitHub stars~2.5k tokensUpdated today
    Media & CreativeAuto-check: notes

  • Transcribe

    JetBrains/skills

    Official

    Transcribe audio files to text with optional diarization and known-speaker hints.

    366 GitHub starsUsed in 4 repos~776 tokens
    Media & CreativeAuto-check passed

More from iurysza/module-graph

All 16 skills in this repo

  • Chatgpt Imagegen

    iurysza/module-graph

    Generates or edits raster images through OpenAI's Image API.

    420 GitHub stars~726 tokensUpdated 2 days ago
    Auto-check passed

  • Gemini Tts

    iurysza/module-graph

    Generates spoken MP3 audio from text or Markdown with Gemini TTS.

    420 GitHub stars~968 tokensUpdated 2 days ago
    Auto-check passed

  • Skill Cleaner

    iurysza/module-graph

    Audits installed Agent Skills for duplicates, unused candidates, loaded roots, oversized descriptions, and prompt cost.

    420 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed

  • Brainstorming

    iurysza/module-graph

    Explores and validates a feature, component, workflow, or behavior change before implementation.

    420 GitHub stars~723 tokensUpdated 2 days ago
    Auto-check passed

  • Domain Modeling

    iurysza/module-graph

    Maintains project domain language, context maps, diagrams, and architectural decisions under ai-artifacts.

    420 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Reply Bro

    iurysza/module-graph

    Rewrites technical review replies as short, natural Slack or PR messages between engineers.

    420 GitHub stars~501 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Audio Transcribe

What does Audio Transcribe do?

Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps. Audio Transcribe is an agent skill from iurysza/module-graph.5 Transcribe, including speaker labels and provider timestamps.

When should I use Audio Transcribe?

Audio Transcribe fits situations like: similar recordings; tasks that involve Transcription.

How do I install Audio Transcribe in Claude Code?

Run `npx skills add iurysza/module-graph --skill audio-transcribe -a claude-code`. Or copy the skill folder (.agents/skills/audio-transcribe in iurysza/module-graph) into .claude/skills/audio-transcribe in your project. Claude Code loads it when a task matches its description.

How do I install Audio Transcribe in Codex?

Run `npx skills add iurysza/module-graph --skill audio-transcribe -a codex`. Or copy the skill folder (.agents/skills/audio-transcribe in iurysza/module-graph) into .agents/skills/audio-transcribe in your project. Codex loads it when a task matches its description.

Can I use Audio Transcribe in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iurysza/module-graph --skill audio-transcribe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audio-transcribe, .gemini/skills/audio-transcribe, .github/skills/audio-transcribe and .opencode/skills/audio-transcribe in your project.

What does Audio Transcribe need to run?

Going by SKILL.md and its folder, Audio Transcribe needs TypeScript for the scripts in its folder, the command-line tools its instructions call (bun) and credentials named GOOGLE_API_KEY, OPENCODE_GOOGLE_API_KEY and GEMINI_API_KEY. Our summary lists: Node.js; A credential in GEMINI_API_KEY; A credential in GOOGLE_API_KEY. Compatibility (from SKILL.md): Requires Bun 1.1+, ffmpeg/ffprobe, network access, and a Gemini API key..

Does Audio Transcribe access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audio Transcribe safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Audio Transcribe use?

Audio Transcribe is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audio Transcribe use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audio Transcribe?

Skills that share tags, products or a category with Audio Transcribe: HyperFrames Media Use (heygen-com/hyperframes, 60k stars), Native Subtitle Quote Image (chengyi-ai/native-subtitle-quote-image, 2.6k stars), Edu Chem Video (wy51ai/edulab, 1.4k stars) and Transcription Memory Reconstruction (NxcoreAI/EverRoom, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audio Transcribe?

iurysza (a GitHub user) maintains it in iurysza/module-graph, which has 420 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 8, 2026.

Source: iurysza/module-graph on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.