Fruitful Registry
Home › Business
WhisText icon

WhisText

Recording to summary & minutes
US flag US
1 of 1 storefronts
Content in en-US
Age Rating
4+
Years
Developer
Language
EN
+1 More
Size
45.9
MB

Information

Apple ID6754094086
Bundle IDcom.ozn.dev.WhisText
SellerSeller
Min iOS17.0
Min macOS14.0
Device familiesiphone, ipad
Released2025-10-17
Copyright© 2025 Koji Ozono
WebsiteLink ↗
Privacy policyLink ↗

Preview 2 platforms

iPhone 5 images

iPhone screenshot
iPhone screenshot
iPhone screenshot
iPhone screenshot
iPhone screenshot

iPad 5 images

iPad screenshot
iPad screenshot
iPad screenshot
iPad screenshot
iPad screenshot

What’s New Version 1.2.7

- Added storage management feature (you can now check the total size of audio files and delete unnecessary audio data from the settings screen) - Fixed an issue where the language selection screen would appear every time at launch for some language settings - Improved stability

Description

Just tap record, and the app automatically generates a transcript, summary, and meeting minutes. It also supports importing audio files and OCR transcription from camera/photos. Generated content can be posted automatically to Slack. Audio files and transcripts are deleted from the server immediately after processing. Main Features - Tap record for instant transcription - Insert timeline markers to flag key moments on the spot (adjustable in 5-second increments) - Transcript highlighting synced to playback position - Automatic summary and meeting minutes generation via AI (custom prompts supported) - Automatic posting to Slack - OCR transcription from images (batch processing for multiple images) Fast, Multilingual Processing - NVIDIA Parakeet (25+ languages including English, German, French, Spanish, Italian, and Japanese) and Paraformer (Chinese) both process at 30x+ speed. *Unsupported languages and mixed-language audio will process more slowly. *Processing speed may vary depending on the server load. - Other/mixed languages: multilingual models (e.g., Whisper) - Server-side processing to minimize battery consumption Recording & Import - Tap to record → instant transcription - Import audio files (Share Sheet supported) - Automatically extract and compress audio from video files - Import images for OCR (processed on-device) Export & Integration - Export as audio, text, summary, minutes, or subtitles (VTT, SRT) - Automatic posting to Slack Privacy & Security - Audio files and transcripts are deleted from the server immediately after processing. No data is retained. Supported Formats - Audio: mp3, m4a, aac, wav, flac, ogg, opus, wma, amr, mpga, webm, aiff, caf - Video: mp4, mov, m4v, webm, mkv, avi, mpeg, mpg *Recognition accuracy may vary depending on audio quality and content.

Accessibility

ipadiphonemacrealityDevicetvoswatch

Version history 18 versions

Build 887471134v1.2.72026-06-26 14:29:44
- Added storage management feature (you can now check the total size of audio files and delete unnecessary audio data from the settings screen) - Fixed an issue where the language selection screen would appear every time at launch for some language settings - Improved stability
Build 887441757v1.2.52026-06-25 18:07:01
- Added “Auto-detect” for speaker language. - Fixed an issue with incorrect language detection.
Build 887457166v1.2.62026-06-25 22:52:00
- Fixed an issue where the progress percentage was not displayed correctly.
Build 887387655v1.2.42026-06-24 15:16:10
- Made speaker language selection mandatory, and fixed a bug where the language setting alert was not displayed in some environments.
Build 887261490v1.2.22026-06-22 03:01:22
- Minor adjustments to the screen design - Fixed minor bugs
Build 887274890v1.2.32026-06-22 13:35:43
- Removed LLM language selection from the settings.
Build 887202392v1.2.12026-06-19 23:40:07
- Added support for displaying processing progress (%)
Build 887074774v1.2.02026-06-17 14:18:30
- Added channel picker for Slack integration - Added OAuth Scopes guidance inside the app for Slack token setup - Screen turns black while recording - Added a language selection prompt on first launch - Updated speech recognition model description to reflect current setup
Build 886020354v1.1.02026-05-22 18:40:11
- Adjustments related to changes in the speech recognition model.
Build 882521737v1.0.72026-03-20 15:41:05
We have switched to a slower server to maintain free availability and reduce processing costs.
Build 883596757v1.0.82026-03-20 22:29:39
Fixed an issue that caused the app to crash in certain situations, improving stability.
Build 880433237v1.0.62025-12-08 21:54:34
・Improved timeline display and added VAD (silence removal) processing.
Build 879186511v1.0.52025-10-23 21:09:46
• Adjusted the community link behavior in the Settings screen — it now opens via an HTML redirect for improved compatibility.
Build 879154442v1.0.42025-10-22 21:51:21
• Added a link to the community thread on X in the Settings screen. You can now join the official community directly from the app.
Build 879055850v1.0.32025-10-20 06:41:50
•Fixed an issue where push notifications were not received on Mac.
Build 879047415v1.0.12025-10-18 14:21:32
•Fixed an issue where push notifications were not delivered correctly.
Build 879052633v1.0.22025-10-18 21:15:39
•Add FFmpeg-driven audio conversion
Build 878996241v1.0.02025-10-17 22:03:12

No pricing data captured yet — comparisons appear once the app has paid storefronts or in-app purchases.

Availability 1 of 1 storefronts

RegionLanguagePriceRatingsAvgVersion
US en-USFree01.2.7

Change log 22 changes · US

releaseNotes updated
- Added storage management feature (you can now check the total size of audio files and delete unnecessary audio data from the settings screen) - Fixed an issue
description updated
Just tap record, and the app automatically generates a transcript, summary, and meeting minutes. It also supports importing audio files and OCR transcription fr
subtitle updated
Recording to summary & minutes
name updated
WhisText
Version 1.2.7 released
- Added storage management feature (you can now check the total size of audio files and delete unnecessary audio data from the settings screen) - Fixed an issue where the language selection screen would appear every time at launch for some
Version 1.2.6 released
- Fixed an issue where the progress percentage was not displayed correctly.
Version 1.2.5 released
- Added “Auto-detect” for speaker language. - Fixed an issue with incorrect language detection.
Version 1.2.4 released
- Made speaker language selection mandatory, and fixed a bug where the language setting alert was not displayed in some environments.
Version 1.2.3 released
- Removed LLM language selection from the settings.
Version 1.2.2 released
- Minor adjustments to the screen design - Fixed minor bugs
Version 1.2.1 released
- Added support for displaying processing progress (%)
Version 1.2.0 released
- Added channel picker for Slack integration - Added OAuth Scopes guidance inside the app for Slack token setup - Screen turns black while recording - Added a language selection prompt on first launch - Updated speech recognition model desc
Version 1.1.0 released
- Adjustments related to changes in the speech recognition model.
Version 1.0.8 released
Fixed an issue that caused the app to crash in certain situations, improving stability.
Version 1.0.7 released
We have switched to a slower server to maintain free availability and reduce processing costs.
Version 1.0.6 released
・Improved timeline display and added VAD (silence removal) processing.
Version 1.0.5 released
• Adjusted the community link behavior in the Settings screen — it now opens via an HTML redirect for improved compatibility.
Version 1.0.4 released
• Added a link to the community thread on X in the Settings screen. You can now join the official community directly from the app.
Version 1.0.3 released
•Fixed an issue where push notifications were not received on Mac.
Version 1.0.2 released
•Add FFmpeg-driven audio conversion
Version 1.0.1 released
•Fixed an issue where push notifications were not delivered correctly.
Version 1.0.0 released
expanded screenshot