Live Transcribe

Last updated
Live Transcribe
Developer(s) Google Research
Initial releaseFebruary 4, 2019;5 years ago (2019-02-04)
Stable release
6.6.602963593 [1] / February 5, 2024;2 months ago (2024-02-05)
Operating system Android
Size 4mb
Type Accessibility
License Open Source
Website www.android.com/accessibility/live-transcribe/

Live Transcribe is a smartphone application to get realtime captions developed by Google for the Android operating system. Development on the application began in partnership with Gallaudet University. [2] It was publicly released as a free beta for Android 5.0+ on the Google Play Store on February 4, 2019. [3] As of early 2023 it had been downloaded over 500 million times. [4] The app can be installed from an .apk file by sideloading and it will launch, but the actual transcription functionality is disabled, requiring creation of an account with Google.

Contents

Development

Researchers Dimitri Kanevsky, Sagar Savla and Chet Gnegy at Google developed the app in collaboration with researchers at Gallaudet University, [5] an American university for the education of the deaf and hard of hearing. The app uses machine learning to generate captions, [6] similar to YouTube's auto-generated captions. [7]

Features

The app uses automatic speech recognition to generate live captions in over 80 languages with varying accuracy. [8] [9] The app, which requires connection to the Internet to function, is available to download on the Google Play Store.

A later update to the app [10] displayed information on sounds such as clapping, laughter, music, applause, and whistling. [11]

In August 2019, Google made the code for Live Transcribe open-source. [12] [13]

In May 2020, the app started supporting transcription in Albanian, Burmese, Estonian, Macedonian, Mongolian, Punjabi, and Uzbek, supporting 70 languages. [14]

In March 2022, the app was updated with support to transcribe offline, without Internet connection, so long as the appropriate language pack has been installed. [15] The offline mode is only available for devices with 6GB of RAM and certain Google Pixel devices.

Related Research Articles

<span class="mw-page-title-main">Google Contacts</span> Contact management tool from Google

Google Contacts is a

Transcription software assists in the conversion of human speech into a text transcript. Audio or video files can be transcribed manually or automatically. Transcriptionists can replay a recording several times in a transcription editor and type what they hear. By using transcription hot keys, the manual transcription can be accelerated, the sound filtered, equalized or have the tempo adjusted when the clarity is not great. With speech recognition technology, transcriptionists can automatically convert recordings to text transcripts by opening recordings in a PC and uploading them to a cloud for automatic transcription, or transcribe recordings in real-time by using digital dictation. Depending on quality of recordings, machine generated transcripts may still need to be manually verified. The accuracy rate of the automatic transcription depends on several factors such as background noises, speakers' distance to the microphone, and accents.

<span class="mw-page-title-main">Google Play</span> Digital distribution service by Google

Google Play, also known as the Google Play Store or Play Store and formerly Android Market, is a digital distribution service operated and developed by Google. It serves as the official app store for certified devices running on the Android operating system and its derivatives, as well as ChromeOS, allowing users to browse and download applications developed with the Android software development kit (SDK) and published through Google. Google Play has also served as a digital media store, offering games, music, books, movies, and television programs. Content that has been purchased on Google Play Movies & TV and Google Play Books can be accessed on a web browser and through the Android and iOS apps.

<span class="mw-page-title-main">Google Keep</span> Note-taking service developed by Google

Google Keep is a note-taking service included as part of the free, web-based Google Docs Editors suite offered by Google. The service also includes: Google Docs, Google Sheets, Google Slides, Google Drawings, Google Forms and Google Sites. Google Keep is available as a web application as well as mobile app for Android and iOS. The app offers a variety of tools for taking notes, including texts, lists, images, and audio. Text from images can be extracted using optical character recognition and voice recordings can be transcribed. The interface allows for a single-column view or a multi-column view. Notes can be color-coded and labels can be applied to notes to categorize them. Later updates have added functionality to pin notes and to collaborate on notes with other Keep users in real-time.

<span class="mw-page-title-main">Wear OS</span> Smartwatch operating system by Google

Wear OS is a version of Google's Android operating system designed for smartwatches and other wearables. By pairing with mobile phones running Android version 6.0 "Marshmallow" or newer, or iOS version 10.0 or newer with limited support from Google's pairing application, Wear OS integrates Google Assistant technology and mobile notifications into a smartwatch form factor. Wear OS is closed-source, in contrast to the free and open-source Android.

<span class="mw-page-title-main">Google Fit</span> Health-tracking platform by Google

Google Fit is a health-tracking platform developed by Google for the Android operating system, Wear OS, and iOS. It is a single set of APIs that blends data from multiple apps and devices. Google Fit uses sensors in a user's activity tracker or mobile device to record physical fitness activities, which are measured against the user's fitness goals to provide a comprehensive view of their fitness.

<span class="mw-page-title-main">Speech Recognition & Synthesis</span> Screen reader application by Google

Speech Recognition & Synthesis, formerly known as Speech Services, is a screen reader application developed by Google for its Android operating system. It powers applications to read aloud (speak) the text on the screen, with support for many languages. Text-to-Speech may be used by apps such as Google Play Books for reading books aloud, Google Translate for reading aloud translations for the pronunciation of words, Google TalkBack, and other spoken feedback accessibility-based applications, as well as by third-party apps. Users must install voice data for each language.

Google Talkback is an accessibility service for the Android operating system that helps blind and visually impaired users to interact with their devices. It uses spoken words, vibration and other audible feedback to allow the user to know what is happening on the screen allowing the user to better interact with their device. The service is pre-installed on many Android devices, and it became part of the Android Accessibility Suite in 2017. According to the Google Play Store, the Android Accessibility Suite has been downloaded over five billion times, including devices that have the suite preinstalled.

<span class="mw-page-title-main">Gboard</span> Virtual keyboard app for Android and iOS

Gboard is a virtual keyboard app developed by Google for Android and iOS devices. It was first released on iOS in May 2016, followed by a release on Android in December 2016, debuting as a major update to the already-established Google Keyboard app on Android.

<span class="mw-page-title-main">Google Allo</span> Instant messaging app by Google

Google Allo was an instant messaging mobile app by Google for the Android and iOS mobile operating systems, with a web client available in some web browsers. It closed on March 12, 2019.

Google Duo was a proprietary voice over IP (VoIP) and videotelephony service released in 2016 by Google and merged into its Google Meet product in 2022. It was available for Android, IOS and web browsers. It let users make and receive one-to-one and group audio and video calls with other Duo users in high definition, using end-to-end encryption by default. Duo could be used either with a phone number or a Google account, allowing users to call someone from their contact list.

<span class="mw-page-title-main">Google Lens</span> Image recognition tool developed by Google

Google Lens is an image recognition technology developed by Google, designed to bring up relevant information related to objects it identifies using visual analysis based on a neural network. First announced during Google I/O 2017, it was first provided as a standalone app, later being integrated into Google Camera but was reportedly removed in October 2022. It has also been integrated with the Google Photos and Google Assistant app and with Bard as of 2023.

<span class="mw-page-title-main">Files (Google)</span> File management software

Files is a file management app developed by Google for file browsing, media consumption, storage clean-up and offline file transfer. It was released by Google on December 5, 2017 with a custom version for China being released on May 30, 2018.

Crowdsource is a crowdsourcing platform developed by Google intended to improve a host of Google services through the user-facing training of different algorithms.

<span class="mw-page-title-main">Android 10</span> Tenth major version of the Android mobile operating system

Android 10 is the tenth major release and the 17th version of the Android mobile operating system. It was first released as a developer preview on March 13, 2019, and was released publicly on September 3, 2019.

<span class="mw-page-title-main">Otter.ai</span> Transcription software company

Otter.ai, Inc. is a Mountain View, California-based technology company that develops speech to text transcription applications using artificial intelligence and machine learning. Its software, called Otter, shows captions for live speakers, and generates written transcriptions of speech.

<span class="mw-page-title-main">Google Meet</span> Video-conferencing software developed by Google

Google Meet is a video communication service developed by Google. It is one of two apps that constitute the replacement for Google Hangouts, the other being Google Chat. It replaced the consumer-facing Google Duo on November 1, 2022, with the Duo mobile app being renamed Meet and the original Meet app set to be phased out.

<span class="mw-page-title-main">Google Messages</span> Messaging application developed by Google

Google Messages is a text messaging software application developed by Google for its Android and Wear OS mobile operating systems, while it's also available via the Web.

<span class="mw-page-title-main">Nearby Share</span> Data transfer program by Google

Nearby Share was a functionality developed by Google that allows data to be transferred between devices via Bluetooth, Wi-FI Direct or Internet. In 2024, it was merged into Samsung's Quick Share. It was available for Android, ChromeOS and Microsoft's Windows. It was first released on August 4, 2020.

References

  1. "Live Transcribe & Notification APKs". APKMirror. Retrieved April 13, 2024.
  2. "Meet the Deaf Developer Behind Google's Live Transcribe App". 2019-02-07. Retrieved 2021-01-23.
  3. Dieter Bohn (2019-02-04). "Google Live Transcribe could be a big help for people who are deaf or hard of hearing". TheVerge.
  4. "Live Transcribe & Notification". Google Play. Retrieved 2023-02-11.
  5. "As ADA turns 30, tech is just getting started helping people with disabilities". 2020-07-27. Retrieved 2021-01-23.
  6. "Real-time Continuous Transcription with Live Transcribe". Google AI Blog. Retrieved 2021-02-15.
  7. "Google's Sagar Savla Built An App That Can Help 466 Million People Who Can't Hear Communicate". Times of India. 2020-01-06. Retrieved 2021-02-15.
  8. Giridharan, Vignesh (2019-07-15). "Here's how Google is putting AI to work in healthcare, environmental conservation, agriculture and more | Digit". digit.in. Retrieved 2021-02-15.
  9. Live Transcribe Team (2020-12-08). "Best Practices for Live Transcribe". Medium. Retrieved 2021-02-15.
  10. Li, Abner (2019-06-03). "Live Transcribe update will recognize laughing, applause". 9to5Google . Retrieved 2021-02-15.
  11. Li, Abner (2019-05-16). "Android Live Transcribe can detect farts, but it won't (for now)". 9to5Google . Retrieved 2021-02-15.
  12. "Google open-sources Live Transcribe's speech engine". VentureBeat. 2019-08-16. Retrieved 2021-02-15.
  13. "Bringing Live Transcribe's Speech Engine to Everyone". Google Open Source Blog. Retrieved 2021-02-15.
  14. "Accessibility updates that help tech work for everyone". Google. 2020-05-21. Retrieved 2022-10-06.
  15. "Google adds an offline mode to the Live Transcribe app". XDA. 2022-03-11. Retrieved 2022-10-06.