I’m building a web app whose core purpose is automation. The front end is written in React, the back end in Flask, and the workflow orchestration will rely on Make.com. Two real-time features sit at the centre of the project: Speech to Text for capturing spoken input and Text to Speech for generating audio responses. I already have high-level wireframes and API notes, and I’m comfortable discussing endpoints, component structure, or Make.com scenarios with you in detail. GHL (GoHighLevel) will also be part of the stack, mainly for CRM-related triggers and webhooks. What I need from you • Extend or build React components that stream audio to the Flask API and display transcription results instantly. • Implement Flask routes that call the chosen Speech-to-Text and TTS services, return results quickly, and log meaningful analytics. • Configure Make.com scenarios so events in the app (e.g., a completed transcription) automatically trigger the relevant actions in GHL. • Ensure the whole flow runs securely, with sensible error handling and token-based authentication. Acceptance looks like this: a user speaks, sees the live transcript inside the React UI within seconds, presses “Play”, and hears the TTS output, while a webhook confirms completion in GHL—all orchestrated through Make.com and passing automated tests. If this matches your skill set, let’s talk timelines and milestones—code first, polish later.