# Azure AI transcription py

> Azure AI transcription py is an open-source agent skill for design and media. Lets your agent write Python code for Azure speech-to-text, batch and real-time. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py
- **Repository:** https://github.com/microsoft/skills
- **GitHub stars:** 3,214
- **License:** MIT
- **Skill name:** azure-ai-transcription-py
- **Collection:** https://github.com/microsoft/skills
- **Categories:** design and media, cloud and infrastructure, AI models and LLM tooling
- **Listing updated:** 2026-11-18

## About

This skill guides an AI coding agent through building speech-to-text features with the Azure AI Transcription client library for Python. It covers installing the package, configuring an endpoint and either key-based or Entra ID authentication, and wrapping clients in context managers so connections are released cleanly.

The bundled instructions include example code for two modes: batch jobs that take audio from URLs such as blob storage and return results with optional speaker diarization, and real-time streaming that sends an audio file and reads back transcription events. The guidance also lists practices such as keeping sync and async clients separate, specifying the locale, capturing timestamps for subtitles, and handling streaming backpressure.

You need an Azure AI Transcription resource with its endpoint and key, or credentials that work with DefaultAzureCredential. Extra reference files cover additional operations and non-core scenarios.

## When your agent uses it

> Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization. Triggers: "transcription", "speech to text", "Azure AI Transcription", "TranscriptionClient".

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py)
- [License: MIT](https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py)

## Features

- **Batch transcription jobs:** Shows how to submit audio files from URLs for asynchronous transcription and check job status.
- **Real-time streaming:** Covers streaming audio to the service and iterating over transcription events as they arrive.
- **Speaker diarization:** Demonstrates enabling speaker separation for recordings with multiple voices.
- **Authentication setup:** Explains key-based auth and Entra ID credentials through environment variables.
- **Client lifecycle guidance:** Recommends context managers and consistent sync or async usage to release resources.
- **Reference material:** Points to extra files on non-core capabilities and production checklists.

## Good for

- Transcribe a recorded meeting with separate speaker labels
- Generate timestamped subtitles from an audio file
- Convert live speech into text with a streaming client
- Batch process long audio files stored in cloud storage
- List previous transcription jobs from the service

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/azure-ai-transcription-py` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/azure-ai-transcription-py &&
cp -R "$tmp/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py" ~/.claude/skills/azure-ai-transcription-py &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/azure-ai-transcription-py` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/azure-ai-transcription-py` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/azure-ai-transcription-py &&
cp -R "$tmp/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py" ~/.agents/skills/azure-ai-transcription-py &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/azure-ai-transcription-py` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/azure-ai-transcription-py` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/azure-ai-transcription-py &&
cp -R "$tmp/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py" ~/.cursor/skills/azure-ai-transcription-py &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/azure-ai-transcription-py` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/microsoft/skills.git --path .github/plugins/azure-sdk-python/skills/azure-ai-transcription-py
```

Or copy the folder to `~/.gemini/skills/azure-ai-transcription-py` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/azure-ai-transcription-py`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/azure-ai-transcription-py &&
cp -R "$tmp/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py" ~/.copilot/skills/azure-ai-transcription-py &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/azure-ai-transcription-py` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/microsoft/skills.git
```

Then copy `skills/.github/plugins/azure-sdk-python/skills/azure-ai-transcription-py` into your agent's skills folder as `azure-ai-transcription-py`. Agents that support SKILL.md read one folder per skill.

## FAQ

### What do I need before using this skill?

You need the azure-ai-transcription package installed, an endpoint URL for your Azure resource, and either a subscription key or Entra ID credentials.

### Which languages does the skill cover?

The examples and guidance are written for Python using the azure-ai-transcription package.

### Does the skill run any scripts?

No. It contains only instructions and code examples plus reference files.

### How do I install Azure AI transcription py in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/azure-ai-transcription-py to use it in all your projects, or to .claude/skills/azure-ai-transcription-py in one project.

### Does Azure AI transcription py run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Azure AI transcription py?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to Azure AI transcription py?

The closest alternatives to Azure AI transcription py are Skill creator, Rea tool design, Prototype, Codebase design and Slack GIF creator.

## Where this comes from

- Description: from the skill's own SKILL.md.

## Alternatives

- [Skill creator](https://ai-powered.com/skills/skill-creator): Skill creator is a free agent skill for ai models and llm tooling.
- [Rea tool design](https://ai-powered.com/skills/rea-tool-design): Rea tool design is an open-source agent skill for design and media.
- [Prototype](https://ai-powered.com/skills/prototype): Prototype is an open-source agent skill for developer tools.
- [Codebase design](https://ai-powered.com/skills/codebase-design): Codebase design is an open-source agent skill for design and media.
- [Slack GIF creator](https://ai-powered.com/skills/slack-gif-creator): Slack GIF creator is a free agent skill for communication.
- [Theme factory](https://ai-powered.com/skills/theme-factory): Theme factory is a free agent skill for design and media.
- [PPTX](https://ai-powered.com/skills/pptx): PPTX is a free agent skill for files and documents.
- [MCP builder](https://ai-powered.com/skills/mcp-builder): MCP builder is a free agent skill for ai models and llm tooling.

---
Source: https://ai-powered.com/skills/azure-ai-transcription-py
