n8n Interview Coach Workflow: Whisper + GPT-4.1 TTS

Turn every interview question into a voice-first coaching session

This n8n Interview Coach Workflow receives a candidate’s audio via webhook, transcribes it with OpenAI Whisper, analyzes delivery metrics, and then responds with a spoken coaching feedback using OpenAI GPT-4.1 TTS—including a next interview question and structured scoring.

What this workflow does

• Webhook-based intake: Handles a POST webhook request with sessionId, role (optional), turnNumber, and an audio recording from the candidate.
• Speech-to-Text (Whisper): Sends the audio to OpenAI Speech-to-Text (Whisper) to generate a transcript.
• Delivery metrics analysis: Computes coaching-relevant signals such as filler-word usage, words per minute, pace assessment, short-answer flags, and whether the session reached the final turn.
• Session-aware coaching: Uses an OpenAI chat agent with Window Buffer Memory keyed by sessionId to produce structured JSON feedback, encouragement, a score, and a follow-up question (or a wrap-up on the final turn).
• Text-to-Speech response: Converts the coaching output and next question into audio via OpenAI Text-to-Speech (GPT-4.1 TTS).
• Delivery confirmation: Waits for a delivery-confirmation callback; then returns the transcript, coaching outputs, score, next question, and generated audio—or sends a retry message if not confirmed.

Use cases

• Mock interview coaching for job candidates using voice recordings.
• Interview practice for SaaS recruiters who want consistent, session-based feedback and scoring.
• Founder-led hiring enablement where automation engineers need an end-to-end n8n voice loop.

Technical details

• OpenAI integration for Whisper transcription and Text-to-Speech (GPT-4.1 TTS).
• n8n nodes/workflow building blocks mentioned: webhook, wait, set, code, if, plus workflow notes (sticky note).
• Session state handled via Window Buffer Memory keyed by sessionId.

Best for n8n users, automation engineers, and SaaS operators who want a production-style, webhook-driven voice interview coach with measurable delivery coaching.