s-l-h/cat
A basic toolkit for speech analytics, using GPT and Whisper-X
This tool helps you quickly understand what happened in audio conversations like sales calls, customer service interactions, or meetings. You upload an audio file, and it gives you a written transcript, identifies who spoke when, summarizes key points, lists action items, and even analyzes the overall mood. It's designed for anyone who needs to review and extract insights from spoken interactions without listening to the entire recording.
No commits in the last 6 months.
Use this if you need to quickly transcribe, summarize, and understand the core content and sentiment of spoken conversations from audio files.
Not ideal if you primarily need to analyze unstructured text documents or require highly specialized, domain-specific linguistic analysis beyond general summarization and sentiment.
Stars
9
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/s-l-h/cat"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Kieirra/murmure
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
Softcatala/whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
pavelzbornik/whisperX-FastAPI
FastAPI service on top of WhisperX
royshil/obs-localvocal
OBS plugin for local speech recognition and captioning using AI