Speech-to-Text Transcription Specialist Using OpenAI Whisper

We are seeking an experienced transcription specialist proficient in using OpenAI Whisper or similar speech-to-text engines. Your primary responsibility will be to convert audio files into accurate, text-based transcripts. The ideal candidate will have a strong understanding of speech recognition technology and be able to deliver high-quality, error-free transcripts.

NLP techniques (keyword detection, phrase classification, sentiment a plus)

We are developing a lightweight system capable of:

Capturing short ambient audio clips (10–30 seconds)

Transcribing them automatically using Whisper (or similar ASR)

Analyzing the transcribed text using AI or NLP techniques to detect specific language patterns (e.g. repeated phrases, aggressive wording, key trigger terms)

The goal is to build a simple and efficient pipeline that can process real-time or batch audio input and notify a backend or client app if certain criteria are met.

We do not require UI/UX for now — just the backend logic and a minimal interface to test the process (console, webhook, or text output is fine).

If you are detail-oriented and passionate about improving accessibility through accurate transcription, we would love to hear from you. Apply tot his job