voice-transcribe

voice-transcribe is a skill for Claude Code, Codex from TheSmokeDev/taskchad-os. It costs 53 tokens per session (469 once invoked), scanned A, original, MIT.

A speech-to-text step that converts incoming voice notes and audio messages into text before the agent processes them.

In plain words
What is it for?
Use it to transcribe voice notes from chat channels, pass the transcript to the router, and remove temporary audio files afterward.
Why use it?
It lets the normal text-based chat system understand spoken messages without requiring a separate voice conversation flow.

Skill for Claude CodeCodex

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

Good fit Use it to transcribe voice notes from chat channels, pass the transcript to the router, and remove temporary audio files afterward.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thesmokedev/taskchad-os/voice-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 TheSmokeDev/taskchad-os --skill voice-transcribe
Clone the repo
git clone --depth 1 https://github.com/TheSmokeDev/taskchad-os

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 voice-transcribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/voice-transcribe/github.svg)](https://agentmods.dev/skills/thesmokedev/taskchad-os/voice-transcribe)
Your own site
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/voice-transcribe"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/voice-transcribe/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for voice-transcribe

Your own site · 80×15
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/voice-transcribe"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/voice-transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 27
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00053 $0.00469
Opus 5 $0.00026 $0.00234
Sonnet 5 $0.00011 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 8d ago against content hash 6aa45e500134, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

voice-transcribe scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://api.openai.com/v1/audio/transcriptions \
optional-skills/communication/voice-transcribe/SKILL.md · 45 lines

What it actually says

Voice Transcribe

Convert a voice note into text so the normal chat pipeline can handle it. This runs as a pre-processing step on inbound audio, before routing.

Pipeline

  1. Receive — the channel adapter saves the audio attachment to a temp path.
  2. Transcribe — run speech-to-text (preference order):
    • OpenAI Whisper API if OPENAI_API_KEY is set (fast, no local deps):
      curl -s https://api.openai.com/v1/audio/transcriptions \
        -H "Authorization: Bearer $OPENAI_API_KEY" \
        -F model=whisper-1 -F [email protected]
      
    • Local faster-whisper if no key is configured and CPU/GPU allows.
  3. Inject — replace the message body with the transcript, tag it [voice], and hand it to the router as if the user had typed it.
  4. Clean up — delete the temp audio file after transcription.

Notes

  • WhatsApp/Telegram voice notes are usually .ogg (Opus). Whisper accepts it directly; faster-whisper may need ffmpeg installed.
  • Keep the original duration in metadata so the agent can say "got your 0:42 voice note" when useful.
  • Transcription is read-only — no capability gate needed. The reply still goes out through the normal gated chat.send path.
  • Never persist raw audio beyond the transcription step unless the user opts in.
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. 8d ago First seen · 45 lines · 53 tokens per session scan A 6aa45e500134

Subscribe to this mod's changes

voice-transcribe is a skill published in the GitHub repository TheSmokeDev/taskchad-os (24 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 469 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

graphify

Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…

mycelium-hq/ai-brain-starter · 111 tokens

insights

Use when the user types /weekly or /monthly, asks for a weekly or monthly journal review or retrospective, asks 'how was my week' or 'how was my month', or wants trends, anomalies, or patterns across recent journal entries. Also fires when regenerating an insight report for a past week or month. NOT for writing…

mycelium-hq/ai-brain-starter · 91 tokens

setup-brain

Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.

mycelium-hq/ai-brain-starter · 66 tokens

second-brain-mapping

Use when the user wants to map or remap their second brain, refresh the vault's queryable metadata index, extract structured frontmatter from typed notes (books, meetings, people, journals, goals), fill wikilink gaps, or surface cross-type insights and patterns no single file shows. Triggers: /second-brain-mapping…

mycelium-hq/ai-brain-starter · 116 tokens

sunday-review

Use when the user asks for the weekly meta-review or Sunday wrap-up of their week and vault: says /sunday, /sunday-review, 'let's do the weekly review,' 'Sunday review,' 'review my week,' 'weekly retro,' 'week in review,' 'end-of-week review,' or wants journals, patterns, vault health, and stale decisions reviewed…

mycelium-hq/ai-brain-starter · 102 tokens

cierre-de-llamada

Use when a SALES or CLIENT call just ended and the follow-up needs to be produced from its transcript. Triggers: /cierre, "close out this call", "acabo de tener una llamada", "arma el seguimiento", "what's the follow-up on this call", "qué sigue con este cliente", or the user pastes a sales-call transcript. Produces…

mycelium-hq/ai-brain-starter · 0 tokens