Hello Transcribe 4+

Ben Nortier

    • 5.0 • 1 Rating
    • Free
    • Offers In-App Purchases

Description

Hello Transcribe is a private and secure speech to text transcriber that uses OpenAI Whisper and Whisper.cpp.


• All processing is done on-device for 100% privacy, and it also works offline.

• Saved results are encrypted in iCloud.

• Transcribe voice notes (e.g. WhatsApp), podcasts, or any audio file (many formats supported).

• Use multiple Model Configs to choose between fast or accurate transcription (even on-the-fly).

• Dictate text or do live transcription using the microphone.

• Transcribe MP4 video.

• Export VTT or SRT files to add subtitles to video.

• Supports many languages.

* Translate audio from many languages to English.


Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

What’s New

Version 3.2.7

3.2.7

- Fix crash for devices without Metal support & revert to CPU

- Upgrade to Whisper.cpp 1.5.1


3.2.6

- Add support for Cantonese for Large V3.

- Fix Hebrew language bug.


3.2.4

- Support for Whisper 1.5 with Metal and removal of CoreML. Big performance improvement over CoreML but a massive speed improvement for Medium and Large (which didn't have CoreML). On an M1 Max a 400% increase for Large. On an iPhone 14 Pro 100% increase for Medium.

- Support new Large-V3 model from OpenAI.

- Support beam search size of 0 (= Greedy).

- New fast abort mechanism (will abort or stop immediately where before it could take a long time when using big model).

Ratings and Reviews

See All
5.0 out of 5
1 Rating

1 Rating

2dtarget ,

Great app, sometimes crashes though

Very easy way to get access to whisper in your own phone. Also great that there is a free version (although the tiny model is far from perfect). A bug is stopping from using the larger model (accurate), every time I try to select it (I’m premium) the app crashes. Please fix it soon! Thanks

Developer Response ,

Hi, sorry about that crash. Seems like older iPhones can't handle the larger CoreML models. I've added a warning that that might happen, and I will add an option to disable CoreML. That way you can still use the larger models, but won't have the performance boost unfortunately.

Slonimoska ,

Useful app , does not allow default model to be set

Starting with a shortcut it always defaults to tiny model which is bit rubbish

captainbeanbag ,

Pretty buggy

The app seems to crash whenever I try to save a transcript. Also the transcription quality is pretty poor (but I don’t think that the developer is to blame for that!). Finally: subscription pricing for an on device app like this just seems excessive.

Developer Response ,

Hi, thanks. I have identified a bug when saving transcriptions for large files. I have a fix which will be in version 2.1 in the next week or so.

App Privacy

The developer, Ben Nortier, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy.

Data Not Collected

The developer does not collect any data from this app.

Privacy practices may vary based on, for example, the features you use or your age. Learn More

Supports

  • Family Sharing

    Some in‑app purchases, including subscriptions, may be shareable with your family group when Family Sharing is enabled. Learn More

You Might Also Like

See All
Vienna Scribe
Utilities
Whisper Transcribe - Dictation
Utilities
AI Transcription:Local Whisper
Utilities
GeePeeTee
Utilities
Do Not Type - Say & Transcribe
Utilities
AI Actions for Shortcuts
Utilities