Help · We read everything
Support
Something not working, or a question that isn't answered below? Get in touch — a real person reads every message.
Email: support@visionspeech.app. When reporting a problem, it helps to mention your visionOS version and what you were doing when it happened.
Frequently asked
How do I dictate?
Tap the orb (or the record button in Studio) to start, speak naturally, then tap again to stop. The transcript is copied to your clipboard automatically — paste it into any app.
Which languages are supported?
Twenty-five languages, detected automatically. You do not pick a language — just speak, and the model figures it out. You can even switch languages mid-sentence.
Why does it download ~500 MB the first time?
That is the speech model. It downloads once, then transcription runs entirely on your headset — no network needed afterward, and nothing you say is ever uploaded.
The model download failed or got stuck.
Make sure you are on Wi-Fi with room to spare for the ~500 MB model, then retry from Settings. If it still fails, force-quit and reopen the app, or delete and reinstall — there are no accounts, so you lose nothing.
The app cannot hear me.
VisionSpeech needs microphone access. Check Settings ▸ Privacy & Security ▸ Microphone on your Apple Vision Pro and confirm VisionSpeech is enabled, then try recording again.
Can it paste directly into other apps?
visionOS does not allow apps to type into other apps, so VisionSpeech copies the transcript to your clipboard and you paste it where you want it — one gesture.
Where are my past transcripts?
Your last 100 transcripts are kept locally on the device. Open the history to revisit, edit, copy, or delete them. Clearing history or deleting the app removes them for good.
What do you require?
Apple Vision Pro running visionOS 26 or later.
Privacy
VisionSpeech processes your speech on-device and collects no data. For the full details, read the privacy policy.