audio-transcribe

audio-transcribe is a skill for Claude Code, Codex from sonichi/sutando. It costs 42 tokens per session (508 once invoked), scanned A, original, MIT.

A tool that converts audio files and voice notes into written transcripts using Gemini 2.5 Flash. Chat bridges for Slack, Discord, and Telegram can use it to include the spoken content in a task.

In plain words
What is it for?
Use it to transcribe supported formats such as M4A, MP3, OGG, WAV, WebM, AAC, FLAC, and MP4, either directly or through connected chat bridges.
Why use it?
It lets an agent understand voice messages as text, while a failed transcription still leaves the attached file available instead of blocking the task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to transcribe supported formats such as M4A, MP3, OGG, WAV…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonichi/sutando/audio-transcribe
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 sonichi/sutando --skill audio-transcribe
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, 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 audio-transcribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/audio-transcribe.svg)](https://agentmods.dev/skills/sonichi/sutando/audio-transcribe)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/audio-transcribe"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/audio-transcribe.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 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.
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 $0.00042 $0.00508
Opus 5 $0.00021 $0.00254
Sonnet 5 $0.00008 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 7d ago against content hash a8c6fb367a8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audio-transcribe 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.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/audio-transcribe/SKILL.md · 52 lines

What it actually says

audio-transcribe

Transcribes audio files (voice notes, clips) to text via Gemini 2.5-flash. Used by the Slack, Discord, and Telegram bridges to surface voice-note content in task bodies so the core agent can act on the words instead of a bare file path.

How it works

skills/audio-transcribe/scripts/transcribe.py <audio_file_path>

Reads the file, sends it inline (base64) to the Gemini 2.5-flash generateContent endpoint, and prints the transcript to stdout. Exits 0 on success, 1 on any failure (unsupported format, missing API key, network error, API error).

Fail-open design. Every bridge wraps the call in a helper that returns None on a non-zero exit. A failed transcription never blocks the task — the [File attached: /path] line still goes through so the agent can at least see a file was sent.

Supported formats

.m4a (Slack voice clips), .mp3, .ogg, .oga, .opus, .wav, .webm, .aac, .flac, .mp4

Key resolution order

  1. GEMINI_API_KEY or GOOGLE_API_KEY in the process environment
  2. <workspace>/.env (resolved via resolve_workspace())
  3. $CLAUDE_CONFIG_DIR/channels/slack/.env
  4. $CLAUDE_CONFIG_DIR/channels/discord/.env
  5. $CLAUDE_CONFIG_DIR/channels/telegram/.env

Bridge integration

Each bridge calls _transcribe_via_skill(local_path) after downloading a file. The helper locates the skill script relative to src/ (or the app bundle), runs it, and returns the transcript string or None. The bridge then appends either:

  • [Voice transcript: <text>] — when transcription succeeds
  • [File attached: /path] — when skill is absent or transcription fails

Removing the skill

Delete skills/audio-transcribe/ — all three bridges fall back to [File attached:] automatically. Core services are unaffected.

Files

What ships with it

2 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. 7d ago First seen · 52 lines · 42 tokens per session scan A a8c6fb367a8e

Subscribe to this mod's changes

audio-transcribe is a skill published in the GitHub repository sonichi/sutando (392 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 508 once invoked, about $0.0002 per session on Opus 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.