Whisper Transcription 4+
Voice, Speech, Audio Dictation
Good Snooze
-
- Free
- Offers In-App Purchases
Screenshots
Description
Quickly and easily transcribe audio files into text with state-of-the-art transcription technology Whisper. Whether you're recording a meeting, lecture, or other important audio, Whisper for Mac quickly and accurately transcribes your audio files into text.
*Features
- Easily record and transcribe audio files
- Just drag and drop audio files to get a transcription
- All transcription is done on your device, no data leaves your machine
- .srt & .vtt subtitles export
- Get accurate text transcriptions in seconds (~15x realtime)
- Supports Metal and GPU processing for ultra fast performance
- Search the entire transcript and highlight words
- Audio playback and syncing to transcripts
- Supports multiple languages (fastest model is English only)
- Copy the entire transcript or individual sections
- Reader Mode
- Edit and delete segments from the transcript
- Select transcription language (or use auto detect)
- Supported formats: mp3, wav, m4a, mp4, mov, ogg and opus
- Supports Tiny (English only), Small, Base, Medium, Large-V2, Large-V3 models
- Batch transcribe multiple files and export to multiple formats at the same time (srt, vtt etc)
- Export to Word, PDF or HTML websites
- Transcribe system audio (such as Zoom meetings and any other audio)
- Transcribe podcasts by adding audio files for each speaker. The transcript will be generated and split up per speaker..
Pro Unlock
Whisper Transcription is free and lets you transcribe audio with the Tiny and Base models. They're fast and very accurate, but for the best results you should consider upgrading to Pro to use the Tiny (English), Medium and Large models, for industry leading transcription quality. Depending on your usecase you might want to use the Large version. You can always upgrade to the Pro version later. Pro also lets you batch transcribe multiple files, record system audio, transcribe podcasts and more.
* Supported Languages
Whisper for Mac can transcribe audio in 100 different languages:
English, Chinese, German, Spanish, Russian, Korean, French, Japanese, Portuguese, Turkish, Polish, Catalan, Dutch, Arabic, Swedish, Italian, Indonesian, Hindi, Finnish, Vietnamese, Hebrew, Ukrainian, Greek, Malay, Czech, Romanian, Danish, Hungarian, Tamil, Norwegian, Thai, Urdu, Croatian, Bulgarian, Lithuanian, Latin, Maori, Malayalam, Welsh, Slovak, Telugu, Persian, Latvian, Bengali, Serbian, Azerbaijani, Slovenian, Kannada, Estonian, Macedonian, Breton, Basque, Icelandic, Armenian, Nepali, Mongolian, Bosnian, Kazakh, Albanian, Swahili, Galician, Marathi, Punjabi, Sinhala, Khmer, Shona, Yoruba, Somali, Afrikaans, Occitan, Georgian, Belarusian, Tajik, Sindhi, Gujarati, Amharic, Yiddish, Lao, Uzbek, Faroese, Haitian Creole, Pashto, Turkmen, Nynorsk, Maltese, Sanskrit, Luxembourgish, Myanmar, Tibetan, Tagalog, Malagasy, Assamese, Tatar, Hawaiian, Lingala, Hausa, Bashkir, Javanese, Sundanese.
Whisper was made by building on top of all the hard work from Georgi Gerganov, check out his Whisper implementation here: https://github.com/ggerganov/whisper.cpp
Subscriptions will automatically renew unless auto-renew is turned off at least 24 hours before the end of the current period and will be charged to your iTunes account. You can turn off auto-renew/manage subscriptions in your iTunes Account Settings after purchase. Terms of Use & Privacy policy can https://impresskit.net/press-release/f5537c9f-c2c1-42d9-a870-6cecd28a8c31.
What’s New
Version 11.1
■ New
• The search bar now shows how many matching words were found in your transcript
• Added the option to use Voice Activity Detection for WhisperKit models. This will increase your transcription speed and will remove issues related to empty chunks of audio. Try it from Settings > Advanced (Pro)
• You can now choose to only show the app in the Dock, the menubar or both
• Individual words will now by highlighted during playback when using a WhisperKit model.
■ Improvements
• The html export now changes background and text colors based on light and dark mode
• Dictations will no longer show up in clipboard history managers such as Alfred
• Added a button to create a new folder when choosing your save location
• The video player playback speed matches the audio playback if you increase or decrease the speed
• If a Whisper model can not be loaded on launch, the next best model will be loaded
• You can now increase and decrease the font size with ⌘- and ⌘+
• You can increase or decrease the playback speed of the player with the left and right bracket buttons on your keyboard
• The copy button now takes into account the display mode you have selected
• Whisper files show a nicer filename
• The export preview text now shows your entire transcript
• When translating you will see a "Translating..." indicator
• The sidebar now animates nicely when switching between full and compact mode
• You can now add timestamps and speaker names when using AI features.
• You can now remove translations by right clicking them in the sidebar
• Added quick options for combining segments to sentences and for removing "- " at the start of segments
Bugfixes
• You can't click the "Start" button in global mode anymore when no models are loaded
• When starting playback by clicking on a segment, the video player will now be sync
Ratings and Reviews
Very helpful app
On starting, I failed to download the correct 'model' as it is called without which you can't select the files to transcribe. Once I got that right I have found this really, really helpful. My iMac M1 is not provided with enough memory to run the most accurate but slower transcription (!) but in fact one of the faster ones is perfect for what I want. In the settings there is a Find and Replace where you can supposedly train the app to transcribe particular words but I am not sure how well it works yet. The app could be improved but the Pro version is a reasonable price for unlimited access. I'm not even sure how much one would need the Pro version, and anyway you have a week to check it out first. This has saved me many, many hnours to hard typing!
It's a fantastic start, but...
The times I've used it so far, it's been buggy. I'm yet to be able to get it do a proper search / replace and the really key feature of putting names to blocks of texts I can't find a way to get working. I don't mind any of these things if I can get in touch with the devs but reaching out so far hasn't had any results.
The fact that it picks up on non-vocal elements is really useful in the environment I'm in: dogs barking, sigh, coughing, singing, wind blowing and even 'trumpet sounding'. It's the only time I've ever seen this and not even Otter was able to do that at the last iteration. If I could see evidence of the devs committing to it with a proper website (rather than just contacting dead air via Twitter), & new the bugs would be ironed out I'd invest in the pro version in a flash as would many of my colleagues.
Verdict: a great start but please build out the support & fix the bugs.
Works pretty well, but not perfect
For a free app this does a great job compared to all the other transcription options and there's no online services.
I haven't tried the Pro version for comparison but I'd imagine it can will put it on par with Siri or better.
It's better than the other options because it timestamps the transcription and this can be used for a variety of workflows.
What I'd like to see is a realtime dictation implementation akin to Apple's built-in dictation (double-tap the function key in a text area) with live transcription - I'm not sure if this is possible with this application architechture, especially if it uses ffmpeg in the backend which is how I'd approach it.
App Privacy
The developer, Good Snooze, 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 Linked to You
The following data may be collected but it is not linked to your identity:
- Usage Data
Privacy practices may vary based on, for example, the features you use or your age. Learn More
Information
- Provider
- Jordi Bruin
- Size
- 20 MB
- Category
- Utilities
- Compatibility
-
- Mac
- Requires macOS 14.0 or later.
- Languages
-
English, Dutch
- Age Rating
- 4+
- Copyright
- © Good Snooze 2024
- Price
- Free
- In-App Purchases
-
- Year Subscription £29.99
- Whisper Pro £79.99
- Weekly Subscription £4.99
- Monthly Subscription £7.99
- Assistant Monthly £8.99
Supports
-
Family Sharing
Some in‑app purchases, including subscriptions, may be shareable with your family group when Family Sharing is enabled.