Speechius

Product Introduction

1. Definition: Speechius is a desktop teleprompter application for macOS and Windows that utilizes on-device automatic speech recognition (ASR) to create an intelligent, voice-controlled presentation assistant. It falls under the technical categories of presentation software, speech-to-text utilities, and productivity tools for content creators.
2. Core Value Proposition: Speechius exists to eliminate the friction of manual script scrolling during live presentations, enabling speakers to deliver content naturally while maintaining eye contact with their audience. Its core proposition is a hands-free, voice-controlled teleprompter that operates with 100% privacy and remains undetectable on screen-share, all for a one-time purchase price with no subscription.

Main Features

1. On-Device Automatic Speech Recognition (ASR): Speechius uses local machine learning models to process your audio input in real-time, without sending data to the cloud. The ASR engine identifies spoken words and automatically scrolls the script, keeping the current word highlighted. This offline speech recognition ensures privacy and low latency.
2. Undetectable Mode (Excluded from Capture): The application uses operating system-level APIs to request exclusion from screen capture and screen-sharing sessions. This means the Speechius window is removed from the video feed in Zoom, Google Meet, Microsoft Teams, OBS (Open Broadcaster Software), and system screen recordings, making it invisible to your webinar or virtual meeting audience.
3. Slide Trigger Automation: Users can define specific keywords or phrases within their script that, when spoken, send configurable keyboard shortcuts (like the right arrow key) to advance slides in presentation software like PowerPoint or Keynote. This enables hands-free slide control synchronized with the spoken script.
4. Adjustable Reading Line & Transparency: The reading line (a visual anchor) can be dragged to align with the user's camera lens, promoting natural eye contact. Combined with adjustable window opacity, this allows the speaker to read the script while simultaneously viewing the underlying application (e.g., a slide deck) or maintaining a direct gaze into the camera.
5. Live Transcript & Manual Navigation: A real-time transcript in the toolbar displays the last words recognized, providing immediate feedback on system accuracy. If the ASR drifts, users can instantly click to navigate to any word in the script or use toolbar buttons to step forward/backward word-by-word for precise control.

Problems Solved

1. Pain Point: The awkwardness and distraction of manually controlling a teleprompter (via foot pedal, keyboard, or mouse) during a live presentation, which breaks eye contact and flow. It also solves the risk of an audience seeing the prompter window during a screen-share.
2. Target Audience: Webinar hosts, online course creators, video presenters, corporate communicators, podcasters recording on camera, and anyone who delivers scripted or semi-scripted content live to an audience via video conferencing or recording software.
3. Use Cases: Delivering a live product launch webinar without looking down; recording a polished online course video from a script while maintaining a conversational tone; presenting quarterly results on a Teams call without losing place; streaming a scripted presentation on Twitch or YouTube via OBS without visible prompts.

Unique Advantages

1. Differentiation: Unlike traditional teleprompter software that requires manual pacing or hardware pedals, Speechius is entirely voice-paced. Unlike cloud-based transcription services, it processes all audio locally. Unlike subscription-based SaaS tools, it is a one-time purchase desktop app.
2. Key Innovation: The integration of real-time, on-device ASR specifically for pacing a teleprompter, combined with system-level screen capture exclusion, creates a unique, private, and seamless presentation workflow that is not dependent on internet connectivity or peripheral hardware.

Frequently Asked Questions (FAQ)

1. Does Speechius work offline and is my voice data private? Yes, Speechius uses 100% on-device speech recognition; your audio and script text never leave your computer, ensuring complete privacy and offline functionality for presentations.
2. How does the undetectable mode work in Zoom and OBS? The app requests the operating system (macOS or Windows) to exclude its window from the screen capture stream. This means Zoom, OBS, and other capture tools receive a video feed without the Speechius window, though a physical camera pointed at your monitor would still see it.
3. Is Speechius a subscription service? No, Speechius is a one-time purchase license. The price includes 12 months of software updates; after this period, your version continues to work indefinitely, and you can optionally pay to renew update access.
4. Can I use Speechius to control my PowerPoint slides automatically? Yes, by setting up slide trigger words in your script. When you speak the trigger word, Speechius can send a keystroke command to advance your slides in PowerPoint, Keynote, or other presentation software, enabling hands-free control.
5. What are the system requirements for Speechius? Speechius requires macOS 13 (Ventura) or newer (on Apple Silicon or Intel), or Windows 10/11. A functioning microphone is necessary for the speech recognition to operate.