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.
npx skills add sonichi/sutando --skill audio-transcribegit clone --depth 1 https://github.com/sonichi/sutandoWrote 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.
[](https://agentmods.dev/skills/sonichi/sutando/audio-transcribe)<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>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.
| Model | Per session | Once 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 | $0.00051 |
Grade A, and why
audio-transcribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
audio-transcribe
Transcribes audio files (voice notes, clips) to text via Gemini 2.5-flash. Used by the Slack, Discord, and Telegram bridges to surface voice-note content in task bodies so the core agent can act on the words instead of a bare file path.
How it works
skills/audio-transcribe/scripts/transcribe.py <audio_file_path>
Reads the file, sends it inline (base64) to the Gemini 2.5-flash generateContent endpoint, and prints the transcript to stdout. Exits 0 on success, 1 on any failure (unsupported format, missing API key, network error, API error).
Fail-open design. Every bridge wraps the call in a helper that returns None
on a non-zero exit. A failed transcription never blocks the task — the
[File attached: /path] line still goes through so the agent can at least see
a file was sent.
Supported formats
.m4a (Slack voice clips), .mp3, .ogg, .oga, .opus, .wav, .webm,
.aac, .flac, .mp4
Key resolution order
GEMINI_API_KEYorGOOGLE_API_KEYin the process environment<workspace>/.env(resolved viaresolve_workspace())$CLAUDE_CONFIG_DIR/channels/slack/.env$CLAUDE_CONFIG_DIR/channels/discord/.env$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.
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.
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.
- 7d ago First seen · 52 lines · 42 tokens per session scan A a8c6fb367a8e
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.
Other skills, from other repositories
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
media-processing
Ingest and process media files (video, audio, image).
visualize
Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.
fish-audio
Generate expressive audio clips using Fish Audio S2 TTS with bracket emotion tags. Record voice memos, narration, audio messages, or any spoken content.
vellum-sounds
Customize the desktop app's sound effects by adding sound files to the workspace, enabling sounds, setting volume, and assigning sounds to app events.
voice-setup
Complete voice configuration in chat - desktop Talk and PTT shortcuts, microphone permissions, ElevenLabs/Deepgram TTS, and troubleshooting.