superwhisper Realtime is grayed out or missing: the three reasons, and how to turn it on
By Ryleigh Newman · Published
Realtime in superwhisper shows your words on screen while you speak. When the toggle is missing or grayed out, the docs give exactly three reasons: the mode uses a voice model that cannot stream, you do not have a Pro license, or Identify Speakers is on. Here is each one, and how to turn Realtime on.
I built YapToText, a different dictation app for the Mac, so read what I say about superwhisper with that in mind. Every fact about superwhisper here comes from its own docs, read on October 10, 2026.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
This guide in other languages: العربية, Čeština, Dansk, Deutsch, Ελληνικά, Español, Suomi, Français, עברית, हिन्दी, Magyar, Bahasa Indonesia, Italiano, 日本語, 한국어, Norsk, Nederlands, Polski, Português, Română, Русский, Slovenčina, Svenska, ไทย, Türkçe, Українська, Tiếng Việt, 简体中文, 繁體中文
Models that support Realtime
From superwhisper's docs, Realtime toggle missing or grayed out, read October 10, 2026. Cohere Transcribe and the Whisper models do not stream.
| Model | Runs | Needs internet |
|---|---|---|
| Nova 3, Nova 2, Nova Medical | In the cloud | Yes |
| Scribe, from ElevenLabs | In the cloud | Yes |
| Parakeet | On your device | No |
Why the toggle is grayed out
- The voice model. The mode uses a model that cannot stream, such as Cohere Transcribe or a Whisper model. Switch the mode to Nova, Scribe or Parakeet.
- The license. Realtime needs a Pro license.
- Identify Speakers. With Scribe and Nova models, Realtime and Identify Speakers cannot be on together. Turn Identify Speakers off to use Realtime.
Turning it on
- Open superwhisper and go to the mode you want.
- In the mode editor, set Voice Model to a Nova, Scribe or Parakeet model.
- The Realtime toggle becomes available. Turn it on.
If you want live text and no internet connection, Parakeet is the only one of the three that runs on your Mac. The best superwhisper model page compares the models, and Parakeet against Whisper explains the difference between the two families.
Live text in YapToText
superwhisper from its docs, read October 10, 2026. YapToText from its own settings.
| superwhisper Realtime | YapToText | |
|---|---|---|
| What you see | Words on screen as you speak | Your words form in the panel as you speak |
| Models | Nova, Scribe or Parakeet | Works with its Whisper models too |
| Default | A toggle per mode | Live transcription preview, on by default |
| Cost | Pro license | Free. Costs extra battery with Whisper models |
| Typing as you speak | Not described in this doc | Type text live as you speak, an experimental setting, off by default |
In YapToText the preview is what you watch, and the final text still lands when you stop, after cleanup if your mode uses it. VoiceInk's live preview page covers the same question for VoiceInk.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
The short version
- Grayed out. A Whisper or Cohere model, no Pro license, or Identify Speakers on.
- Models that stream. Nova and Scribe in the cloud, Parakeet on the Mac.
- Turn it on. Mode editor, Voice Model, then Realtime.
- Offline and live. Use Parakeet.
If superwhisper changes which models stream, open an issue on GitHub and I will update this page. Every one gets read.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
Related
Sources
- https://superwhisper.com/docs/common-issues/realtime (checked 2026-10-10)
- https://github.com/ryleighnewman/YapToText (checked 2026-10-10)
- https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-10)
Questions
Why is superwhisper Realtime grayed out?
The mode uses a model that cannot stream, such as a Whisper model, you do not have Pro, or Identify Speakers is on with a Nova or Scribe model.
Which superwhisper models support realtime?
Nova 3, Nova 2, Nova Medical and Scribe in the cloud, and the Parakeet models on your device.
Does superwhisper Realtime work offline?
Only with Parakeet, which runs on your device. Nova and Scribe need an internet connection.
Can I use Realtime and Identify Speakers together in superwhisper?
Not with Scribe or Nova models. Turn one off.
Does YapToText show text while I speak?
Yes. Live transcription preview is on by default and works with its Whisper models.