Captionify

Name: Captionify
Rating: 5 (1 reviews)
Author: Jonathan Gregorio

Real-time Captions, AI Summary

Free

1 Rating
Age Rating

4+
Years
Category

Education
Developer

Jonathan Gregorio
Language

EN
English
Size

180.4
MB

Captionify is a powerful, privacy-focused tool for real-time speech recognition and translation. Built for accessibility and global communication, Captionify uses the on-device Moonshine Voice model or Apple Intelligence model (for iOS devices that support) to provide high-accuracy transcriptions and translations without ever sending your audio to the cloud. Powered by the public Moonshine Voice project, and Apple Intelligence for transcript summaries. Key Features: - Real-time Transcription and Translation: High-performance, on-device speech-to-text using Moonshine Voice. - Instant Translation: Seamlessly translate between 7+ languages using Apple’s secure Translation framework. - AI Summarization: Get the gist of long meetings or lectures with Apple Intelligence-powered summaries. - Privacy First: All audio processing and translations happen entirely on your device. - Organization: Save transcripts and audio (optional recording and playback), categorize, search and share your transcripts for future reference. - Language Learning: Use your own AI model API key to generate an on demand breakdown and grammar lessons of a selected sentence in the transcript. - Text to speech on translated live captions, transcript, and conversation mode. - Apple Watch companion app: use it as a remote, secondary display for live captions, and an option to use the watch as a mic for the app. 7 languages: English (en-US), Japanese (ja-JP), Spanish (es-ES), French (fr-FR), German (de-DE), Chinese (zh-CN), Korean (ko-KR)

Ratings & Reviews

5.0

out of 5

1 Ratings

Error
Apr 28

burnsac100
There is an error when downloading the tiny model for Spanish. It will not let me download it (Download failed: HTTP 404 for encoder_model.ort)Also, when choosing the default language I want to translate from (i.e., Español), when I close and reopen the app, my preferences for that language are not saved. Also, it doesn’t seem to pick up any Spanish being spoken. If I use the default language (Japanese, I think), it does detect audio of the speaker speaking. But since they aren’t speaking Japanese, it’s not useful. Even though no words in the audio are being detected, I don’t see a location where I can see the saved recordings either. It isn’t under “saved transcripts”, unless that is only for when words are detected.When clicking “start”, the 0:00 on the right never increases. I’m not sure the cause.The green bar indicating it is detecting sound, it will show words, but only on the default language. And I have to click “TV Mode” first and then exit

Developer Response
Thanks for your feedback, we will correct the issues you mentioned. Some are already addressed with the current release. For Spanish you can use the moonlight base model as the tiny one is not available from the moonlight voice project actually.
Error
Apr 28

burnsac100

There is an error when downloading the tiny model for Spanish. It will not let me download it (Download failed: HTTP 404 for encoder_model.ort)Also, when choosing the default language I want to translate from (i.e., Español), when I close and reopen the app, my preferences for that language are not saved. Also, it doesn’t seem to pick up any Spanish being spoken. If I use the default language (Japanese, I think), it does detect audio of the speaker speaking. But since they aren’t speaking Japanese, it’s not useful. Even though no words in the audio are being detected, I don’t see a location where I can see the saved recordings either. It isn’t under “saved transcripts”, unless that is only for when words are detected.When clicking “start”, the 0:00 on the right never increases. I’m not sure the cause.The green bar indicating it is detecting sound, it will show words, but only on the default language. And I have to click “TV Mode” first and then exit
Developer Response 1d ago
Thanks for your feedback, we will correct the issues you mentioned. Some are already addressed with the current release. For Spanish you can use the moonlight base model as the tiny one is not available from the moonlight voice project actually.

Fix proximity pairing stuck: remove NISession, guard double-invite

Version 2.1 5d ago

Data Not Collected

The developer does not collect any data from this app.

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

Accessibility

Information

Seller: Jonathan Gregorio
Size: 180.4 MB
Category: Education
Compatibility: Requires iOS 26.0 or later.

iPhone
Requires iOS 26.0 or later.

iPad
Requires iPadOS 26.0 or later.

Mac
Requires macOS 26.2 or later and a Mac with Apple M1 chip or later.

Apple Vision
Requires visionOS 26.0 or later.

Apple Watch
Requires watchOS 11.0 or later.
Languages: English
Age Rating: 4+

4+

Learn More

Privacy Policy

More by Jonathan Gregorio

View

Zen Kendama

Simulation

Captionify

Ratings & Reviews

Error

What’s New

App Privacy

Data Not Collected

Accessibility

Information

More by Jonathan Gregorio

Zen Kendama