azure-ai-transcription-py
Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill azure-ai-transcription-py88
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
100%
100%Conference Panel Transcription
Batch transcription with diarization
Correct package import
0%
100%
Subscription key auth
0%
100%
Endpoint env var
0%
100%
Key env var
0%
100%
begin_transcription call
0%
100%
content_urls parameter
0%
100%
Locale specified
0%
100%
Diarization enabled
0%
100%
job.result() usage
0%
100%
pip install package
0%
100%
Job name provided
0%
100%
Without context: $0.2359 · 3m 5s · 16 turns · 23 in / 3,678 out tokens
With context: $0.2731 · 1m 39s · 19 turns · 26 in / 2,269 out tokens
84%
65%Live Customer Support Call Transcription
Real-time streaming transcription
Correct package import
0%
100%
Subscription key auth
30%
100%
Endpoint env var
0%
100%
Key env var
0%
100%
begin_stream_transcription call
0%
100%
Locale in stream call
25%
100%
send_audio_file usage
0%
100%
Iterate stream events
0%
100%
event.text access
0%
100%
Session closed
87%
0%
Backpressure handling
87%
0%
Without context: $0.3484 · 4m 43s · 25 turns · 31 in / 4,228 out tokens
With context: $0.1841 · 35s · 14 turns · 50 in / 1,816 out tokens
73%
24%Video Tutorial Subtitle Generation
Timestamp capture for subtitle generation
Correct package import
0%
100%
Subscription key auth
37%
100%
Endpoint env var
0%
100%
Key env var
0%
100%
Batch API used
50%
0%
content_urls used
50%
0%
Locale specified
87%
75%
Timestamps captured
93%
100%
SRT or timed output
100%
100%
job.result() called
14%
0%
pip install package
0%
100%
Without context: $0.2529 · 3m 35s · 17 turns · 23 in / 4,321 out tokens
With context: $0.4992 · 5m 8s · 32 turns · 38 in / 5,727 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.