 | |
 A screenshot of Google Live Transcribe running on aSamsung Galaxy S20 | |
| Developer(s) | Google Research |
|---|---|
| Initial release | February 4, 2019; 6 years ago (2019-02-04) |
| Stable release | |
| Operating system | Android |
| Size | 4 MB |
| Type | Accessibility |
| License | Apache License 2.0[2] |
| Website | www |
Live Transcribe is amobile app for real-time captioning, developed byGoogle for theAndroid operating system. Development on the application began in partnership withGallaudet University.[3] It was publicly released as a free beta forAndroid 5.0+ on theGoogle Play Store on February 4, 2019.[4] As of early 2023 it had been downloaded over 500 million times.[5]
Researchers Dimitri Kanevsky,Sagar Savla and Chet Gnegy at Google developed the app in collaboration with researchers atGallaudet University,[6] an American university for the education of the deaf and hard of hearing. The app usesmachine learning to generate captions,[7] similar to YouTube's auto-generated captions.[8]
In August 2019, Google made Live Transcribe anopen-source project.[9][10]
The app usesspeech recognition to generate live captions in over 80 languages with varying accuracy.[11][12] The app, which requires connection to theInternet to function, is available to download on theGoogle Play Store.
A later update to the app[13] displayed information on sounds such as clapping, laughter, music, applause, and whistling.[14]
In May 2020, the app started supporting transcription in Albanian, Burmese, Estonian, Macedonian, Mongolian, Punjabi, and Uzbek, supporting 70 languages.[15]
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.[16] The offline mode is only available for devices with 6GB of RAM and certain Google Pixel devices.
