stt
Transcribe Audio with verging.ai STT
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.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "stt" from https://skillstore.io/skills/verging-ai-stt.md and its manifest at https://skillstore.io/api/skills/verging-ai-stt/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.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.
Test it
Using "stt". Transcribe a short English product demo recording.
Expected outcome:
The skill returns a plain-language transcript, the detected or requested language, the audio duration, and the credits consumed.
Using "stt". Prepare to transcribe a 20 MB WebM interview file.
Expected outcome:
The skill confirms the format is supported, checks that the file is below 25 MB, and identifies the required API key and credits.
Using "stt". Troubleshoot a failed transcription request.
Expected outcome:
The skill maps common status codes to causes such as unsupported files, insufficient credits, rate limits, or upstream service errors.
Security Audit
Medium RiskThe skill is documentation-only, and most external command detections are false positives from Markdown code fences and inline formatting. The confirmed risks are intentional network calls to verging.ai and external audio disclosure for transcription. The API key detections are placeholders and environment variable examples, not embedded live secrets.
Confirmed security concerns (1)
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
🌐 Network access (4)
🔑 Env variables (2)
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.
Copy report link
https://skillstore.io/skills/verging-ai-stt/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/verging-ai-stt?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/verging-ai-stt?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/verging-ai-stt/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/verging-ai-stt.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
verging-ai. (2026). stt security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/verging-ai-stt/audits/5BibTeX citation
@techreport{verging-ai-verging-ai-stt-2026,
author = {verging-ai},
title = {stt security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/verging-ai-stt/audits/5},
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: "stt security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "verging-ai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/verging-ai-stt/audits/5"
identifiers:
- type: other
value: "skillstore:verging-ai-stt:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Transcribe Team Recordings
Convert meeting recordings into searchable text for notes, summaries, and follow-up tasks.
Process Interview Audio
Turn interview audio into text before analysis, tagging, or documentation work.
Add STT to Developer Workflows
Reference endpoint parameters and response fields while building speech-to-text integrations.
Try These Prompts
Use the stt skill to transcribe recording.mp3 in English. Return the transcript and mention any file limits that apply.
Use the stt skill for a Japanese audio file. Explain which language setting to use before sending the file.
Use the stt skill to summarize the required authentication, endpoint, file format, and credit details for an integration plan.
Use the stt skill to design a transcription workflow for customer calls, including consent checks, API key handling, and error handling.
Best Practices
- Store the verging.ai API key in an environment variable or approved secret manager.
- Confirm consent and data policy requirements before sending audio to an external API.
- Check file format, file size, credits, and language settings before making a request.
Avoid
- Hardcoding a real API key in prompts, scripts, tickets, or shared documentation.
- Uploading confidential recordings without approval from the data owner.
- Sending unsupported or oversized audio files and retrying without checking the error cause.
Frequently Asked Questions
What does this skill do?
Which tools can use it?
Does it require an API key?
What audio formats are supported?
Does it run transcription locally?
What should users check before uploading audio?
Developer Details
Author
verging-aiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
26421118b848d9f1efc0aa169d8a7a9e7e0a877e
Maintenance freshness
7/18/2026
Usage
3 downloads · 0 views