Orate

Why voice-tracked scrolling stops when you record video

Voice-following prompters are the best idea in this category, and they have a specific failure: start recording video and the scroll often stops following you. The cause is architectural, not a bug you can wait out.

Voice-tracked scrolling — the prompter listens to you and moves the script at your actual pace — is the most genuinely useful idea anyone has had in this category. It removes the thing that makes prompter delivery sound like prompter delivery, which is you matching a machine instead of the machine matching you.

It also has a well-known failure mode: it frequently stops following you the moment you start recording video. PromptSmart’s VoiceTrack is the feature people usually mean, and it is the one we looked at closely when deciding what to build. The cause is not a bug in a particular release. It is a resource conflict, and it explains why almost nobody ships both halves working together.

Why voice tracking stops: two things want the microphone

When you record video with voice tracking on, two independent consumers need the same audio input at the same time:

  • The video encoder, which needs a continuous audio stream to mux into the file alongside the picture. A gap here is a gap in your recording.
  • The speech recogniser, which needs the same stream to work out which word you just said and how far down the script you are.

On both iOS and Android, a microphone input is normally handed to one consumer. Two subsystems that each independently ask the operating system for “the microphone” do not quietly share it. One of them wins. Which one depends on ordering, on the audio session category, and on details that change between OS versions — which is why the symptom is inconsistent enough to read like a flaky bug.

The outcomes are all bad in different ways: voice tracking goes silent and the script stops moving, or the recording ends up with no usable audio, or the session drops and capture stops altogether.

Where this figure comes from

We tested competitors while scoping this app and recorded the finding in our decision log: voice-tracked scrolling stopping when recording video with it, with microphone contention as the cause. Snapshot taken August 2026. Apps ship, and any specific app’s behaviour may have changed since — run the test below rather than trusting a dated note, including ours.

The fix, and why few teleprompter apps ship it

There is a correct answer, and it is not a flag you can toggle. The app has to own its audio pipeline: open the microphone once, as a single source it controls, then fan the buffers out to both destinations — a copy to the encoder for the file, and a copy to the recogniser for the scroll position. Neither consumer ever talks to the microphone. Only the app does.

That is real work. It means writing your own capture layer instead of connecting a recording SDK to a speech SDK and hoping, and it means handling route changes, interruptions and sample-rate conversion yourself. It is considerably more expensive than either half alone, which is why the two features exist widely and the combination barely does.

For what it is worth, this is why our capture layer sat behind an interface with exactly one implementation behind it — the seam was there so that owning the audio path later would not require rewriting the app around it. When this post was written, Orate did not ship voice tracking. It does now, and the last section says how, and where it is not yet proven.

Test it yourself in two minutes

Whatever app you are using, this tells you where you stand:

  1. Turn voice tracking on and do not record. Read a few lines. Confirm the script follows you — this proves the recogniser works at all.
  2. Now start recording video and read the same lines at the same pace.
  3. Watch the script rather than yourself. Does it still follow, or has it reverted to a constant crawl, or stopped?
  4. Stop, and play the recording back with the volume up. Check the audio is actually there. An app can keep the tracking working and quietly lose your sound, which is the worse outcome of the two because you will not notice until later.

Do this on the phone you shoot on. It is the kind of behaviour that varies by device and OS version, so somebody else’s result is weak evidence about yours.

What to do while recording

If your app’s voice tracking is unreliable during capture, a calibrated fixed speed is better than an intelligent one that drops out. Three things make fixed-speed scrolling much less robotic than its reputation:

  • Calibrate to yourself, not to a default. Read 20 seconds of your own script aloud, count the words, multiply by three. That is your rate in words per minute, and it is probably not the number the app shipped with. Ours differ by writing system for the same reason — see teleprompter speed by language.
  • Write in short paragraphs with deliberate breaks. A fixed scroll punishes long unbroken blocks, because there is nowhere to catch up. Line breaks give you slack.
  • Record in shorter takes. Drift accumulates. Two ninety-second takes are far easier to keep in sync than one three-minute take, and you will cut between them anyway.

If voice tracking is the only thing you want

Then run the test above in your app before trusting it on a take. If it fails, use voice tracking as a rehearsal and delivery aid, not during capture: track your voice while you practise, then record with a fixed speed you have calibrated. It is two passes instead of one, and it is more reliable than hoping the microphone conflict resolves in your favour on the take that matters.

And if you are recording something you cannot repeat, the more important question is not how the script scrolls but whether the file survives. That one has its own test: does a teleprompter app save your video if it crashes?

Orate’s fix has shipped: Follow my voice

When we wrote this in August 2026, Orate did not follow your voice at all. It does now. The feature is called Follow my voice, it is an option in the recorder’s Speed sheet, and it is built the way this post says the fix has to be built.

  • On iPhone, one audio source. One capture session, and the same microphone buffers go to the recording and to the recogniser. We verified it on an iPhone 15 with a 78-second 4K take, and the audio was intact.
  • On Android, its own microphone feed and a fallback. The camera library owns the microphone, and from Android 13 Orate opens its own microphone feed for the recogniser, which the phone does not silence during a take. We checked a 49-second take on a OnePlus 8T running Android 14, but not every phone, so we do not claim it works on every one. On Android 12, or if a phone still silences the recogniser during a take, the recorder notices (speech on the level meter, nothing recognised for eight seconds) and carries on at a fixed speed from where you are. The take keeps recording either way.
  • On the phone, and nowhere else. Recognition uses the phone’s own on-device recogniser, so nothing you say is sent anywhere, and it works offline once the language is downloaded.
  • It holds rather than guesses. Go off script and the text stops where it is; come back and it picks up from the words you are saying.

Follow my voice is part of Orate Pro and included in the free trial; the prompter and recording are free. It needs iOS 18 or later, or Android 12 or later. The test above applies to us as much as to anyone: run it on the phone you shoot on. The full mechanism is in how a voice-activated teleprompter works.

A teleprompter that keeps following while you record

Follow my voice listens on the phone, holds when you go off script and keeps the take recording. The prompter and recording are free, with no account and no watermark; Follow my voice is part of Pro and included in the free trial.

See Follow my voice
Keep reading