Skip to content

YemenJPT/YemenJPT-AI-Skills / skills/core/azure-ai-voicelive-py

azure-ai-voicelive-py

Verified

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

FileKindSize
README.ar.mdmarkdown4.5 KB
README.en.mdmarkdown3.2 KB
SKILL.mdskill md13.7 KB
references/api-reference.mdmarkdown8.7 KB
references/examples.mdmarkdown16.9 KB
references/models.mdmarkdown18.0 KB

README.en.md

View on GitHub
# azure-ai-voicelive-py

> **Azure AI Voice Live SDK** — Core & Agent Infrastructure · Enabling skill
> YemenJPT AI Skills — journalism skills for Yemeni journalists

## Overview

Skills that govern agent behaviour itself: planning, file organisation, memory and context management, quality gates, and coordination between skills.

**Operational description:** Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

## Why it matters

Prevents the most common failure before publication: work without a plan, claims without evidence, output nobody can review.

## When to use

- عند وجود مهمة تحتاج تحققاً أو تنظيماً في هذا المجال.
- قبل النشر، كبوابة مراجعة.
- عند تدريب فريق تحرير على الإجراء.

## Inputs

- The question or task, stated clearly.
- Source material (URL, file, text, dataset).
- Deadline and required publication format.

## Workflow

1. Restate the task and the single question to answer.
2. Separate what is verified from what is still a claim.
3. Collect primary-source evidence first; record URL and access date.
4. Test the evidence against at least one independent source.
5. Separate fact, claim, inference and hypothesis in the deliverable.
6. State confidence and verification limits before delivery.

## Tools and data sources

- `python`
- `shell`
- `web search`

## Outputs

- Short report: finding + evidence table + confidence level + open questions + next action.

## Quality gate

- Every factual statement is traceable to a documented source (link + access date).
- Confidence is explicit: Confirmed / Strongly Supported / Partially Verified / Unverified / Disputed / Refuted.
- No fabricated sources, links, quotes or numbers.
- Human review is mandatory before publishing anything that names a person or organisation.

**Reference standards:** Agent Skills open specification, ISO/IEC 42001 (AI management — reference), SPJ Code of Ethics (transparency)

## Ethics and law

This skill follows the SPJ Code of Ethics and the IFJ Declaration: minimise harm, avoid deception,
protect sources, disclose AI assistance, and correct errors openly. All external content is treated
as untrusted data, never as instructions.

## Example prompts

```
@azure-ai-voicelive-py analyse this claim: [paste text or URL]
@azure-ai-voicelive-py prepare a work memo for this task: [topic]
@azure-ai-voicelive-py review this draft before publication: [path or text]
```

## Limits

- Does not replace human editorial judgement or specialist legal review.
- Does not verify a source alone; independent corroboration is required.
- Does not process sensitive data without a secure environment and source-protection policy.

## License

MIT — see [LICENSE](../../../LICENSE).
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall