Tool Information
Aiko is an AI-powered audio transcription tool that allows users to easily convert speech to text from meetings, lectures, and more. The transcription is performed directly on the user's device, ensuring complete privacy. Aiko's transcription capabilities are powered by OpenAI's Whisper model, which is capable of transcribing audio in 100 different languages. The app supports audio and video files and offers exporting to many different formats, including JSON, CSV, and subtitles. Aiko is designed to be a simple tool for audio transcription, although it includes support for Shortcuts. For more advanced users, MacWhisper is an alternative tool from the same developer that offers additional features like improved performance on iOS thanks to CoreML and batch conversion. As a privacy-focused app, Aiko does not allow editing of the transcription within the app, and users are encouraged to export and edit the transcription in a proper text editor. Aiko divides the transcription text by sentences, although users can use a workaround to divide the text into paragraphs or fix missing punctuations using a prompt from ChatGPT. While Aiko does not yet support live transcription or diarization, the developer plans to prioritize more popular requests. Aiko is compatible with macOS and iOS devices, and users can easily drag and drop audio files or share recordings from apps like Voice Memos and Telegram for transcription.
F.A.Q
Aiko is an AI-powered audio transcription tool, developed by Sindre Sorhus. It capitalize on the powerful capabilities of OpenAI's Whisper model to convert spoken words to written text directly on the user's device. Aiko can transcribe audio from various engagements such as meetings and lectures. It executes the transcription purely on the user's device, thereby enforcing the complete privacy of the user.
Aiko hosts a variety of features. It can transcribe audio in 100 different languages and supports audio and video files. The transcriptions can be exported to diverse formats like JSON, CSV, and subtitles. There are no editing capabilities within the app, but users are encouraged to export and edit the transcription in a suitable text editor. It also has support for Shortcuts, and it divides transcription text by sentences. Despite its straightforwardness, for advanced needs, users can seek out MacWhisper, which is an alternative tool from the same developer.
Yes, Aiko is compatible with both iOS and macOS devices. The users can easily drag and drop audio files or share recordings from apps like Voice Memos and Telegram directly into the app for transcription.
Aiko supports exporting transcriptions to many different formats, which includes JSON, CSV, and subtitles.
Yes, Aiko supports transcription in multiple languages. Powered by OpenAI’s Whisper model, Aiko can process audio transcription in a hundred different languages.
The Shortcuts in Aiko provides an innovative way for users to integrate Aiko's functionalities into their workflows, providing a more seamless transcription experience.
User privacy is a core feature of Aiko. All transcriptions are processed directly on the user's device, eliminating the necessity for data transfer to external servers or third-party processors. This ensures that all transcriptions remain private and secure.
No, Aiko does not offer an option to edit transcriptions directly within the app. However, users are encouraged to export and edit the transcription in a proper text editor.
For more advanced transcription needs, MacWhisper is suggested as an alternative tool from the same developer. MacWhisper provides additional features like improved performance on iOS with CoreML and batch conversion capabilities.
Currently, Aiko does not provide support for live transcription or diarization. Transcriptions can be obtained by recording the audio first and then transcribing it using the app. However, the developer intends to look into these features but will prioritize features based on demand.
There are several improvements planned for Aiko such as batch conversion, improved performance on iOS thanks to CoreML, export to karaoke file, and an integration with ChatGPT.
Users can request new features, report bugs or give feedback directly on the Sindre Sorhus' website. The feedback product should be stated as 'Aiko'.
Aiko has several advantages over the built-in transcription on Apple devices. Primarily, it offers a much better accuracy, supports more languages, can transcribe both audio and video files, and also provides the ability to export transcriptions to many different formats like JSON, CSV, and subtitles.
The time taken to generate a transcription with Aiko depends on various factors. These include the performance of the device being used for transcription, the amount of available memory and CPU. However, the developer of Aiko plans on significantly increasing the speed of transcription in the coming months.
No, it is not possible to remove some languages from Aiko to save space. The languages are all stored together in a way which makes it impossible to remove some of them.
For transcribing audio from the Voice Memos app on macOS, the user simply needs to drag and drop the memo into the Aiko window. On iOS, the user needs to tap the memo, tap the '...' button, tap 'Share', and choose Aiko in the app list. For a Telegram Voice Note, since macOS/iOS cannot handle the Ogg format in which the notes are stored, a user needs a workaround which involves converting the format of the file to 'AAC' before Aiko can transcribe it.
Although Aiko does not yet support live transcription, users can record a Zoom meeting and after the meeting is finished, drop the recording into the Aiko window to transcribe it.
Yes, Aiko is free. It was developed with the joy of making apps and does not feature advertisements.
Currently, there are no immediate plans to localize the app in different languages.
Users can check for updates or new versions of Aiko on the App Store. There is also a Version History tab available for users to understand the changes and improvements in the software over time.
Pros and Cons
Pros
- Supports 100 languages
- On-device transcription
- Ensures user privacy
- Supports audio and video files
- Exports to JSON
- CSV
- subtitles
- Compatible with macOS
- iOS
- Easy drag and drop audio files
- Transcripts divided by sentences
- Edit transcriptions in any text editor
- ChatGPT for punctuation
- paragraph adjustment
- Upcoming features prioritized by user requests
- Share recordings from apps like Voice Memos
- Telegram
- Uses CoreML for performance improvement on iOS
- Support for Shortcuts
- Native
- written in Swift and SwiftUI
- Free without ads
- Can export transcription as subtitles
Cons
- No live transcription
- No in-app transcription editing
- Divides text by sentences
- Sometimes missing punctuation
- No diarization
- Doesn't support non-native audio formats
- Doesn't support language deletion
- No naming of speakers
- Consumes significant disk space
- Transcription may repeat
Reviews
You must be logged in to submit a review.
No reviews yet. Be the first to review!
