Skills azure-speech-to-text-rest-py

📦

azure-speech-to-text-rest-py

Name: azure-speech-to-text-rest-py
Author: sickn33

Content revision r2 High Risk ⚙️ External commands🌐 Network access🔑 Env variables

Transcribe Short Audio with Azure REST

Short audio transcription often requires unnecessary SDK setup. This skill provides focused Python patterns for calling Azure Speech REST endpoints directly.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

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

Agent request

Review the Skillstore skill "azure-speech-to-text-rest-py" from https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py.md and its manifest at https://skillstore.io/api/skills/sickn33-azure-speech-to-text-rest-py/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/sickn33-azure-speech-to-text-rest-py.md Signed manifest GET /api/skills/sickn33-azure-speech-to-text-rest-py/manifest Signed lockfile GET /api/skills/sickn33-azure-speech-to-text-rest-py/lockfile

Test it

Using "azure-speech-to-text-rest-py". Transcribe a 20-second English WAV recording and return the best text.

Expected outcome:

Recognition succeeded. Best transcription: Remind me to buy five pencils.

Using "azure-speech-to-text-rest-py". Explain why a 90-second recording fails with this endpoint.

Expected outcome:

The short-audio endpoint supports recordings up to 60 seconds.
Use the Speech SDK or Batch Transcription API for longer audio.

Using "azure-speech-to-text-rest-py". Prepare a detailed French transcription request with safe credential handling.

Expected outcome:

Language is set to fr-FR and detailed results are requested.
The subscription key is loaded from the environment.
The Azure region must be validated before building the endpoint.

Security Audit

High Risk

v5 • 7/23/2026 Open versioned report

Most static findings are Markdown syntax, official Azure URLs, or expected environment-based credential handling. The skill performs real external audio transmission, and unchecked region values can redirect credential-bearing requests to an unintended host.

Files scanned

381

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:44-61 SKILL.md:143-168 SKILL.md:192-204 SKILL.md:255-270 SKILL.md:305-322

Unvalidated Region Can Redirect Credential-Bearing Requests

The examples interpolate AZURE_SPEECH_REGION into request hostnames without validation. A crafted value containing URL delimiters can redirect audio or subscription keys to an unintended HTTPS host.

The region value is read from the environment and inserted before an Azure domain suffix without allowlist validation, while sensitive headers are attached to the resulting URL.

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.

Low

SKILL.md:61

Python HTTP libraries

response = requests.post(url, headers=headers, params=params, data=audio_file)

The request sends local audio and an Azure subscription key to an external Speech endpoint; this is intended but remains a real data transfer.

Low

SKILL.md:163

Python HTTP libraries

response = requests.post(

The request streams local audio with an Azure subscription key to an external Speech endpoint; this is intended but remains a real data transfer.

Low

SKILL.md:197

Python HTTP libraries

response = requests.post(

The request transmits the Azure subscription key to an external token endpoint to obtain a bearer token.

Low

SKILL.md:262

Python HTTP libraries

response = requests.post(

The request sends local audio and an Azure subscription key to an external Speech endpoint; this is intended but remains a real data transfer.

Risk Factors

⚙️ External commands (45)

🌐 Network access (15)

SKILL.md:11 SKILL.md:61 SKILL.md:163 SKILL.md:197 SKILL.md:262 SKILL.md:291 SKILL.md:15 SKILL.md:16 SKILL.md:27 SKILL.md:47 SKILL.md:146 SKILL.md:195 SKILL.md:258 SKILL.md:308 SKILL.md:333

🔑 Env variables (21)

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

Copy report link

https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-azure-speech-to-text-rest-py/security.svg)](https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-azure-speech-to-text-rest-py/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-azure-speech-to-text-rest-py.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

sickn33. (2026). azure-speech-to-text-rest-py security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py/audits/5

BibTeX citation

@techreport{sickn33-sickn33-azure-speech-to-text-rest-py-2026,
  author = {sickn33},
  title = {azure-speech-to-text-rest-py security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py/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: "azure-speech-to-text-rest-py security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-azure-speech-to-text-rest-py/audits/5"
identifiers:
  - type: other
    value: "skillstore:sickn33-azure-speech-to-text-rest-py:audit:5"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Prototype Voice Features

Add short command or note transcription to a Python prototype without installing the Speech SDK.

Automate Short Recording Intake

Transcribe brief WAV or OGG submissions through a lightweight service workflow.

Compare Recognition Candidates

Request detailed results and inspect confidence-ranked alternatives for short recordings.

Try These Prompts

Create a Basic Transcriber

Create a Python function that transcribes [audio path] in [language] with Azure Speech REST. Use environment variables for credentials.

Configure an Audio Format

Adapt the transcription request for [WAV PCM or OGG OPUS]. Explain the required content type and validate the duration limit.

Add Production Error Handling

Improve the transcription workflow with timeouts, recognition status handling, safe error messages, and bounded retries for transient failures.

Design an Async Token Workflow

Design an aiohttp transcription client using cached bearer tokens, validated Azure regions, chunked input, and concurrent request limits.

Best Practices

Use WAV PCM at 16 kHz mono when broad compatibility is required.
Validate the region and language before constructing the request.
Set explicit timeouts and handle every recognition status in production.

Avoid

Do not embed subscription keys in source files or prompts.
Do not send recordings longer than 60 seconds to the short-audio endpoint.
Do not log authorization headers, bearer tokens, or sensitive audio content.

Frequently Asked Questions

Does this skill require the Azure Speech SDK?

No. It uses direct HTTPS requests with Python requests or aiohttp.

Which audio formats are covered?

The examples cover WAV PCM at 16 kHz mono and OGG with OPUS.

What is the maximum recording length?

The short-audio endpoint supports recordings up to 60 seconds.

Can it return confidence scores?

Yes. Request the detailed response format to receive ranked candidates and confidence values.

How should credentials be stored?

Store the subscription key in an environment variable or approved secret manager. Never place it directly in source code.

When should another Azure interface be used?

Use the Speech SDK or Batch Transcription API for streaming, interim results, custom models, translation, or longer audio.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/azure-speech-to-text-rest-py

Ref

f9e2c34b4f19c7f3e6b0a1e93227b5f77cc12526

Maintenance freshness

7/26/2026

Usage

7 downloads · 82 views

File structure

📄 SKILL.md