Skills speech-to-text

📦

speech-to-text

Content revision r1 Critical ⚙️ External commands🌐 Network access

Transcribe Audio with Whisper Models

Audio and video recordings are hard to search or reuse without accurate transcripts. This skill uses inference.sh Whisper models to create transcripts, translations, and timestamped segments.

Supports: Claude Codex Code(CC)

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "speech-to-text" from https://skillstore.io/skills/inference-sh-9-speech-to-text.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-speech-to-text/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inference-sh-9-speech-to-text.md Signed manifest GET /api/skills/inference-sh-9-speech-to-text/manifest Signed lockfile GET /api/skills/inference-sh-9-speech-to-text/lockfile

Test it

Using "speech-to-text". A meeting recording URL with English speech.

Expected outcome:

A full transcript with detected English language and paragraph breaks for review.

Using "speech-to-text". A podcast episode URL with timestamp request enabled.

Expected outcome:

A transcript split into timed segments that can guide editing and captions.

Using "speech-to-text". A French audio recording URL with translation requested.

Expected outcome:

An English transcript that preserves the main spoken content.

Security Audit

Critical

v4 • 7/6/2026 Open versioned report

Most Ruby backtick detections are false positives caused by Markdown fences and inline code. The Quick Start contains a confirmed curl-to-shell installer, and its installer URL is part of the same critical remote code execution risk. No prompt injection text or hidden exfiltration intent was found.

1

Files scanned

130

Lines analyzed

1

Review items

0

False positives ignored

Confirmed security concerns (1)

Critical

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh && infsh login

Line 16 pipes a remote installer script directly into sh, which executes mutable network content without prior review. This is a classic remote code execution install pattern.

Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Critical

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh && infsh login

The hardcoded URL is used by curl in a pipe-to-shell installer on the same line. The risk is remote code execution from a mutable external script.

Detected Patterns

Pipe to shell pattern

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Security Assessment

Copy report link

https://skillstore.io/skills/inference-sh-9-speech-to-text/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-9-speech-to-text/security.svg)](https://skillstore.io/skills/inference-sh-9-speech-to-text?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-9-speech-to-text?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-speech-to-text/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-9-speech-to-text.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

inference-sh-9. (2026). speech-to-text security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-speech-to-text/audits/4

BibTeX citation

@techreport{inference-sh-9-inference-sh-9-speech-to-text-2026,
  author = {inference-sh-9},
  title = {speech-to-text security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/inference-sh-9-speech-to-text/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "speech-to-text security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "inference-sh-9"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-9-speech-to-text/audits/4"
identifiers:
  - type: other
    value: "skillstore:inference-sh-9-speech-to-text:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

55

Architecture

85

Maintainability

87

Content

70

Community

83

Spec Compliance

What You Can Build

Create meeting transcripts

Convert recorded meetings into readable text for notes, search, and follow-up tasks.

Prepare podcast transcripts

Turn podcast audio into text that can support editing, summaries, and publishing.

Build subtitle source text

Generate timestamped transcript segments that can be used as caption inputs.

Try These Prompts

Transcribe a meeting

Use this skill to transcribe this meeting audio URL: [audio URL]. Return the full text and detected language.

Generate timestamped text

Transcribe this podcast audio URL with timestamps: [audio URL]. Provide the transcript and segment timing summary.

Translate audio to English

Use Whisper V3 Large to translate this non-English audio URL to English: [audio URL]. Return clear English transcript text.

Create a caption workflow

Extract audio from this video URL, transcribe it with timestamps, and prepare caption-ready text: [video URL]. Show each step.

Best Practices

Use audio sources that you are allowed to process through inference.sh.
Request timestamps when the transcript will support captions or editing.
Review transcripts for names, technical terms, and unclear speech.

Avoid

Do not send confidential recordings without approval from the data owner.
Do not rely on raw transcripts as final legal or medical records.
Do not run remote installer scripts without checking the source and checksum.

Frequently Asked Questions

What audio models does this skill use?

It documents Fast Whisper Large V3 and Whisper V3 Large through inference.sh app IDs.

Can it create timestamps?

Yes. The skill shows timestamped transcription input for segment-level output.

Can it translate audio?

Yes. It includes an example that translates non-English audio to English.

Does it work with video?

It shows a workflow that extracts audio from video before transcription.

Does it require an external service?

Yes. It uses the inference.sh CLI and cloud apps to process transcription requests.

Is the setup command safe for automatic install?

No. The current Quick Start uses a curl-to-shell installer and should be replaced.

Developer Details

Author

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh-9/skills/tree/main/skills/speech-to-text/

Ref

a06681402992ceae98ba04d54cfd4ab004862696

Maintenance freshness

7/18/2026

Usage

11 downloads · 224 views

File structure

More from inference-sh-9

agent-ui

Build React Agent Interfaces

Teams need agent chat interfaces without rebuilding streaming, approvals, and tool displays. This skill guides setup of the inference.sh Agent component in React and Next.js.

Coding & Development View

tools-ui

Add Tool Lifecycle UI to Agent Apps

Agent applications need clear tool status, approval, and result displays. This skill provides React and Next.js component guidance for those workflows.

Coding & Development View

widgets-ui

Render JSON Widgets in React

Agent output often needs interactive UI instead of plain text. This skill shows how to render structured widget definitions as React and Next.js components.

Design & Creative View

chat-ui

Build React Chat Interfaces

Teams need chat interfaces that match modern React apps. This skill provides shadcn-style components and patterns for messages, inputs, avatars, and streaming states.

Coding & Development View

prompt-engineering

Improve AI Prompts for Text, Images, and Video

AI results often fail when prompts are vague or poorly structured. This skill provides reusable patterns for LLM, image, and video prompts.

Productivity View

web-search

Search Web Sources with Tavily and Exa

Research tasks need current web evidence and clean page text. This skill runs inference.sh search and extraction apps for Tavily and Exa.

Research & Learning View

stt

Transcribe Audio with verging.ai STT

by verging-ai

Audio recordings are hard to review, search, and share as text. This skill guides Claude, Codex, and Claude Code through verging.ai speech-to-text transcription using OpenAI Whisper.

Productivity View

lark-minutes

Manage Lark Minutes and Meeting Artifacts

by larksuite

Meeting recordings and transcripts are difficult to search, retrieve, and update consistently. This skill guides Claude, Codex, and Claude Code through supported lark-cli workflows for Lark Minutes.

Productivity View

summarize

Summarize URLs, Files, and Media

by steipete

Long sources make key information difficult to review. This skill uses the Summarize CLI to extract or condense URLs, documents, transcripts, audio, and video.

Productivity View

sonoscli

Control Sonos Speakers from Your AI Assistant

by aiskillstore

Managing Sonos rooms manually slows routine playback and grouping tasks. This skill guides Claude, Codex, and Claude Code through focused Sonos CLI commands.

Productivity View

fal-audio

Create Fal.ai Audio Workflows

by sickn33

Audio tasks need clear steps for generation, transcription, and review. This skill helps Claude, Codex, and Claude Code plan fal.ai audio workflows.

Communication View

azure-ai-transcription-py

Transcribe Audio with Azure AI and Python

by sickn33

Speech transcription projects require correct Azure client setup and workflow choices. This skill provides Python examples for batch and real-time transcription, authentication, diarization, and language selection.

Coding & Development View