transcription software
{{Short description|Software that assists in the conversion of human speech into a text transcript}}
{{more citations needed|date=January 2017}}
Transcription software assists in the conversion of human speech into a text transcript. Audio or video files can be transcribed manually or automatically.{{Cite news|url=https://transcribear.com/transcription.asp|title=Transcription Functions {{!}} Transcribear|last=|first=|date=2017-06-08|work=General Transcription Functions and Conventions, Audio Transcriptions|access-date=2019-02-15}} 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.
Transcription software, as with transcription services, is often used for business, legal, or medical purposes.{{Cite web |title=Medical Transcriptionists |url=https://www.bls.gov/ooh/healthcare/medical-transcriptionists.htm |access-date=2025-02-16 |website=Bureau of Labor Statistics |language=en-us}} Compared with audio content, a text transcript is searchable, takes up less computer memory, and can be used as an alternate method of communication, such as for subtitles and closed captions.
The definition of transcription "software", as compared with transcription "service", is that the former is sufficiently automated that a user can run the entire system without engaging outside personnel. New software-as-a-service and cloud computing models use artificial intelligence, machine learning and natural language processing to convert speech to text and continuously learn new phrases and accents.{{cite web |last1=Bhatt |first1=Medha |title=What is AI Transcription? Everything You Need to Know |url=https://fireflies.ai/blog/what-is-ai-transcription |website=fireflies.ai |access-date=3 June 2022}} AI transcription can, however, lead to hallucinations and other errors.{{Cite web |last=Yang |first=John |date=2025-01-25 |title=What to know about an AI transcription tool that ‘hallucinates’ medical interactions |url=https://www.pbs.org/newshour/show/what-to-know-about-an-ai-transcription-tool-that-hallucinates-medical-interactions#:~:text=Many%20medical%20centers%20use%20an,possibility%20of%20errors%20like%20misdiagnosis. |access-date=2025-02-16 |website=PBS News |language=en-us}}{{Cite web |last=Ananya |date=26 Apr 2024 |title=AI transcription tools ‘hallucinate,’ too |url=https://www.science.org/content/article/ai-transcription-tools-hallucinate-too |url-status=live |access-date=2025-02-16 |website=Science |language=en}}{{Cite web |last=Walker |first=Ben |date=2024-10-31 |title=Whispered Lies: How AI Transcription Sparks Concerns |url=https://www.dittotranscripts.com/blog/whispered-lies-how-ai-transcription-sparks-concerns/ |access-date=2025-02-16 |website=Ditto |language=en-US}}{{Cite web |last=Burke |first=Garance |date=2024-10-26 |title=Researchers say an AI-powered transcription tool used in hospitals invents things no one ever said |url=https://apnews.com/article/ai-artificial-intelligence-health-business-90020cdf5fa16c79ca2e5b6c4c9bbb14 |access-date=2025-02-16 |website=AP News |language=en}}
Development
Research at Google released a free android app Google Live Transcribe, it runs on Google Cloud.{{Cite web|title=Use Live Transcribe - Android Accessibility Help|url=https://support.google.com/accessibility/android/answer/9158064?hl=en|access-date=2021-06-14|website=support.google.com}}{{Cite web|last=Butler|first=Sydney|date=2019-12-09|title=How to transcribe speech using Google's Live Transcribe app|url=https://9to5google.com/2019/12/08/how-to-transcribe-speech-using-googles-live-transcribe-app/|access-date=2021-06-14|website=9to5Google|language=en-US}} Google Chrome developed and has an available built in English Live Caption.{{Cite web|title=Google Chrome's new Live Caption feature will transcribe speech in videos|url=https://techxplore.com/news/2021-03-google-chrome-feature-speech-videos.html|access-date=2021-06-14|website=techxplore.com|language=en}} Google Docs, Google Translate, Google Assistant, GBoard Google Text to Speech engine support transcription tool too.{{Cite web|date=2020-03-17|title=Now you can transcribe speech with Google Translate|url=https://blog.google/products/translate/transcribe-speech/|access-date=2021-06-14|website=Google|language=en-us}}{{Cite web|last=Krasnoff|first=Barbara|date=2020-08-14|title=How to use Google's free transcription tools|url=https://www.theverge.com/21368867/transcription-google-docs-live-transcribe-how-to-zoom|access-date=2021-06-14|website=The Verge|language=en}}{{Cite web|title=Live Transcribe & Sound Notifications - Apps on Google Play|url=https://play.google.com/store/apps/details?id=com.google.audio.hearing.visualization.accessibility.scribe&hl=en_US&gl=US|access-date=2021-06-14|website=play.google.com|language=en}}{{Cite web|title=Google Rolling Out Real-Time Transcription and Translation for Gboard Users|url=https://www.digitalinformationworld.com/2020/08/google-rolling-out-real-time-transcription-and-translation-for-gboard-users.html|access-date=2021-06-14}}
OpenAI launched Whisper, an open-source speech recognition deep learning model in September 2022.{{Cite web |last=Golla |first=Ramsri Goutham |date=2023-03-06 |title=Here Are Six Practical Use Cases for the New Whisper API |url=https://slator.com/six-practical-use-cases-for-new-whisper-api/ |archive-url=https://web.archive.org/web/20230325214704/https://slator.com/six-practical-use-cases-for-new-whisper-api/ |archive-date=2023-03-25 |access-date=2023-08-12 |website=Slator |language=en-US}}