Azure AI Transcription Py

What it does

When your agent uses it

• Real-time and batch speech-to-text transcription with timestamps and diarization
• Tasks that involve Transcription

Example prompts

• “transcription”
• “speech to text”
• “Azure AI Transcription”
• “/azure-ai-transcription-py”

Requirements

• Python 3
• A credential in TRANSCRIPTION_KEY

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Pick sync OR async and stay consistent. Do not mix azure.xxx sync clients with azure.xxx.aio async clients in the same call path. Choose…
2. 2Always use context managers for clients and async credentials. Wrap every client in with Client(...) as client: (sync) or async with…
3. 3Enable diarization when multiple speakers are present
4. 4Use batch transcription for long files stored in blob storage
5. 5Capture timestamps for subtitle generation
6. 6Specify language to improve recognition accuracy
7. 7Handle streaming backpressure for real-time transcription
8. 8Close transcription sessions when complete

What it can do on your machine

Read from SKILL.md and the folder at commit d5741a1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TRANSCRIPTION_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Azure AI Transcription Py loads about 1k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 243 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/skills at commit d5741a1, republished under its MIT licence (© microsoft). 243 words, ~1,021 tokens.

name

azure-ai-transcription-py

description

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".

license

MIT

metadata.author

Microsoft

metadata.version

1.0.0

metadata.package

azure-ai-transcription

pip install azure-ai-transcription

TRANSCRIPTION_ENDPOINT=https://<resource>.cognitiveservices.azure.com
TRANSCRIPTION_KEY=<your-key>  # For key auth; not needed when using DefaultAzureCredential/TokenCredential

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.transcription import TranscriptionClient

with TranscriptionClient(
    endpoint=os.environ["TRANSCRIPTION_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["TRANSCRIPTION_KEY"]),
) as client:
    transcriptions = list(client.list_transcriptions())

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.transcription import TranscriptionClient

with TranscriptionClient(
    endpoint=os.environ["TRANSCRIPTION_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["TRANSCRIPTION_KEY"]),
) as client:
    job = client.begin_transcription(
        name="meeting-transcription",
        locale="en-US",
        content_urls=["https://<storage>/audio.wav"],
        diarization_enabled=True,
    )
    result = job.result()
    print(result.status)

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.transcription import TranscriptionClient

with TranscriptionClient(
    endpoint=os.environ["TRANSCRIPTION_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["TRANSCRIPTION_KEY"]),
) as client:
    stream = client.begin_stream_transcription(locale="en-US")
    stream.send_audio_file("audio.wav")
    for event in stream:
        print(event.text)

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .github/plugins/azure-sdk-python/skills/azure-ai-transcription-py of microsoft/skills.

• SKILL.md
• references/capabilities.md
• references/non-hero-scenarios.md

Open the folder on GitHubat commit d5741a1