How do voice commands work in a teleprompter app?

What voice-activated teleprompter control does

Voice-activated teleprompter control solves a specific problem: how do you control the scroll when you cannot touch the screen? When a phone is mounted on a tripod two feet away, when both hands are holding props or equipment, or when reaching for the screen would interrupt the take, voice commands keep the session running without physical interaction.

This is different from a voice-following teleprompter, which tries to detect speech and automatically advance the text. A voice-following system uses your spoken words to guess pace — which creates problems when you pause, stumble, or change speed. Voice command control uses a single spoken keyword to trigger a precise action: advance three lines, go back three lines, or stop the scroll. The behavior is predictable and repeatable, which matters when you are mid-recording.

For creators, coaches, and educators recording on a phone or tablet without an assistant, voice control provides the same hands-free flexibility that foot pedals give broadcast presenters — without the extra hardware.

The three commands: next, previous, and pause

Teleprompter-Scrolling Scripts uses three voice commands, each triggering a specific action while a Prompter mode session is running.

"Next" advances the script forward. The text moves down, bringing the next section into the reading zone. Use this when you want to jump ahead — skipping a section you know well, moving past a segment you are not using, or catching up after a pause.

"Previous" moves the script backward. The text scrolls up, returning to an earlier position. Use this if you lose your place or want to repeat a section mid-take without stopping the recording.

"Pause" stops the scroll entirely. Say it again and the scroll resumes. This is the most-used command of the three. When you want to hold a moment — let a point land, take a breath, let a separate camera linger — pause stops the text from advancing while whatever else is recording you keeps running. You control the pacing without touching anything.

The simplicity of three commands is intentional. A more complex voice command vocabulary requires more cognitive attention during recording, which is the opposite of what a teleprompter is supposed to do.

When voice control is most useful

Voice control delivers the most value in four recording situations.

The first is tripod recording. When the device is mounted on a stand and positioned for a specific shot, reaching to tap the screen changes the frame or requires moving. Voice commands let you stay in position through the entire take.

The second is prop or product demos. If you are holding something during the recording — a product, a tool, a book — your hands are occupied. Voice commands let you advance the script without putting the prop down.

The third is long-form recording. For extended scripts — course content, detailed tutorials, multi-section explainers — voice commands let you pace the delivery section by section, pausing at natural transitions rather than letting an automatic scroll dictate the rhythm.

The fourth is solo recording without an assistant. On a professional set, someone else can advance the teleprompter. Recording alone, voice commands provide the same capability without a second person in the room.

How to set up voice commands on iPhone and iPad

Voice commands in Teleprompter-Scrolling Scripts are enabled in the app settings before starting a session. Once enabled, the app listens for the three commands — "next," "previous," and "pause" — while a session is active.

Before your first voice-command session, test the commands in a quiet room. Say "next" clearly and confirm the script advances. Say "pause" and confirm the scroll stops. Say "pause" again to confirm it resumes. Then say "previous" and confirm the script moves back. This 30-second test tells you whether the microphone is picking up your voice reliably in the environment you are recording in.

On iPhone and iPad the setup is the same: enable voice control in settings, then run the session in Prompter mode. Make sure the microphone is not blocked by a case, a hand, or a mount when you are speaking commands, since the app is listening on the same input you would speak a command into.

Prompter mode is text-only with no recording, which is what makes it the mode voice control runs in. It suits rehearsals, live speeches, presentations, and any setup where a separate camera, webcam, or video call is capturing you while the device beside you just holds the script.

Voice command accuracy and environment tips

Voice command accuracy depends on background noise and microphone distance. In a quiet room with the device within three to four feet, recognition is reliable. In a louder environment — outdoor recording, a room with HVAC noise, a space with reverb — accuracy can drop.

A few practical adjustments improve reliability in noisy conditions. Speak the command clearly and at normal volume — shouting or whispering both reduce accuracy compared to a clear, conversational delivery. If the command is not recognized on the first attempt, pause briefly and repeat. The app responds to the keyword regardless of surrounding speech, so as long as the word is distinct, it will be picked up.

For critical recordings in difficult acoustic environments, test the commands before the take. Record a short test clip, check that the voice commands are functioning as expected, and proceed. A missed command during a long recording is easy to work around — say the command again — but knowing the system is working before you start reduces uncertainty.

Why voice control is Prompter mode only

Voice control is available in Prompter mode only. The reason is that the other two modes are already using the microphone: Camera mode is capturing the audio track for your video and Voice mode is recording the audio itself. Once the microphone input is committed to a recording, it cannot simultaneously feed speech recognition, so there is no input left for the app to listen for commands on. Prompter mode records nothing, which is exactly what frees the microphone up.

This is a hardware constraint rather than a missing feature, and it is worth understanding because it changes how you plan a shoot. If a take needs both hands-free scroll control and a recording, the recording has to happen somewhere other than the app.

The standard workaround is a two-device setup, which is the same shape professional prompting has always taken. Put the script on one device in Prompter mode with voice control enabled, and let a second device — another phone, a webcam, a DSLR, or a video call — handle the capture. You get hands-free prompting and a recording at the same time, just not from the same piece of hardware. See how the three modes compare for which one a given take needs.

If you are recording single-device in Camera mode or Voice mode, plan on manual scroll control instead: calibrate the automatic scroll speed to your rehearsed pace beforehand, and drag the text by hand if you need to correct mid-take.

Limitations: when to use manual scroll instead

Voice commands work best when the script sections are organized around the command vocabulary. Because "next" and "previous" move a fixed number of lines, scripts with very long paragraphs and no clear breaks are harder to navigate by voice. If you need to land on a specific line mid-paragraph, manual scroll control — tapping the screen or dragging the text — gives you more precision.

In very loud environments — outdoor locations near traffic, rooms with loud music or ambient noise — voice command recognition becomes less reliable. For those situations, a remote Bluetooth clicker or manual screen interaction is more dependable than voice.

Voice control is also not a substitute for a well-paced automatic scroll. If your delivery pace is consistent and the scroll speed is calibrated well, automatic scrolling requires no intervention at all. Voice commands are most valuable when your delivery pace varies, when you need to hold a moment, or when the physical setup makes screen interaction impractical.

The combination of automatic scroll as the default, with voice commands available for manual overrides, gives you the flexibility to handle any recording situation without stopping the take.