fast-transcription
CommunityReal-time call transcription with speaker IDs.
Authorsamelhousseini
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enables rapid transcription of contact center calls with built-in speaker identification, reducing manual review time by delivering per-channel and diarized transcripts in real time or faster-than-real-time.
Core Features & Use Cases
- Stereo channel transcription: agent and customer on separate audio channels for accurate speaker labeling.
- Mono diarization: single-channel recordings with recognized speaker turns and a combined transcript.
- Quick-start guidance for deploying Azure Speech Fast Transcription with minimal setup and secure credential handling.
Quick Start
- Install dependencies from requirements.txt, set AZURE_AI_SPEECH_ENDPOINT and AZURE_AI_SPEECH_KEY in your environment.
- Use the Python API to transcribe with stereo channels or diarization, e.g., a simple call to TranscriptionClient().transcribe_stereo(...) or transcribe_with_diarization(...).
- Review the output: agent and customer transcripts, combined transcript, and basic analytics.
Dependency Matrix
Required Modules
requestspython-dotenvpydub
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: fast-transcription Download link: https://github.com/samelhousseini/microhacks/archive/main.zip#fast-transcription Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.