fast-transcription
Installation
SKILL.md
Fast Transcription Skill
Folder Contents
| File | Type | Description |
|---|---|---|
SKILL.md |
Documentation | Main skill documentation with API reference, speaker ID strategies, and curl examples |
PRD.md |
Documentation | Product Requirements Document for the skill |
.env.sample |
Configuration | Sample environment variables (AZURE_AI_SPEECH_ENDPOINT, AZURE_AI_SPEECH_KEY) |
requirements.txt |
Dependencies | Python package dependencies (requests, python-dotenv, pydub) |
| scripts/ | ||
scripts/__init__.py |
Module | Package initializer with exports |
scripts/transcription_client.py |
Client | Core API client with both stereo and diarization strategies |
scripts/stereo_transcriber.py |
Transcriber | Stereo channel separation for pre-separated audio (agent on ch0, customer on ch1) |
scripts/diarization_transcriber.py |
Transcriber | Mono diarization for mixed-speaker recordings with 2-36 speaker support |
scripts/contact_center_processor.py |
Pipeline | Full contact center pipeline with speaker labeling and call analytics |