Library
Sources
1,784 original sources. Each page says what the source is, why it can be trusted, which facts come from it, and links to the original.
Peer-reviewed research
309 sources. The most used:
- How do People Type on Mobile Devices? Observations from a Study with 37,000 VolunteersKseniia Palin et al., Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI 2019), 2019 · 39 facts
- Observations on Typing from 136 Million KeystrokesVivek Dhakal et al., CHI 2018, ACM Conference on Human Factors in Computing Systems, 2018 · 38 facts
- How We Type: Movement Strategies and Performance in Everyday TypingAnna Maria Feit et al., Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, 2016 · 20 facts
- How many words do we read per minute? A review and meta-analysis of reading rateMarc Brysbaert, Journal of Memory and Language, 2019 · 9 facts
- The use of generative artificial intelligence-based dictation in a neurosurgical practice: a pilot studyBenjamin S. Hopkins et al., Neurosurgical Focus, 2025 · 8 facts
- From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition (full text)Colin Lea et al., Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (arXiv preprint), 2023 · 8 facts
- Automatic Transcription of English and German Qualitative InterviewsSusanne Wollin-Giering et al., Forum: Qualitative Social Research, 25(1), Art. 8, 2024 · 7 facts
- Racial disparities in automated speech recognitionAllison Koenecke et al., Proceedings of the National Academy of Sciences, 2020 · 7 facts
- Comparing Speech and Keyboard Text Entry for Short Messages in Two Languages on Touchscreen PhonesSherry Ruan et al., Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), 2018 · 7 facts
- One-handed touch-typing on a QWERTY keyboardEdgar Matias et al., Human-Computer Interaction, 1996 · 7 facts
Preprint
133 sources. The most used:
- Robust Speech Recognition via Large-Scale Weak Supervision (full text)Alec Radford et al., OpenAI (arXiv), 2022 · 63 facts
- Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition EvaluationHugging Face and collaborators, arXiv, 2025 · 15 facts
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford et al., arXiv (eess.AS), 2022 · 9 facts
- VoxtralMistral AI, arXiv (Audio and Speech Processing), 2025 · 8 facts
- Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic ModelingLucas Rafael Stefanel Gris et al., arXiv (book chapter), 2023 · 6 facts
- Svarah: Evaluating English ASR Systems on Indian AccentsTahir Javed et al., arXiv, 2023 · 6 facts
- Exploring the Impact of Word Prediction Assistive Features on Smartphone Keyboards for Blind UsersMrim M. Alnfiai and Muhammad Ashad Kabir, arXiv preprint (later journal article), 2024 · 5 facts
- Measuring the Accuracy of Automatic Speech Recognition Solutions (HTML version)Korbinian Kuhn et al., arXiv, 2024 · 5 facts
- Automatic Speech Recognition for Non-Native English: Accuracy and Disfluency HandlingMichael McGuire, arXiv, 2025 · 4 facts
- VoiceAgentBench: Are Voice Assistants ready for agentic tasks?Dhruv Jain et al., arXiv, 2025 · 4 facts
Official documentation
513 sources. The most used:
- Dictate your documents in WordMicrosoft, 2026 · 58 facts
- Use voice typing to talk instead of type on your PCMicrosoft, 2026 · 58 facts
- macOS Feature AvailabilityApple, Apple, 2026 · 28 facts
- Dictate messages and documents on Mac (Apple Mac Help, Dictation)Apple Inc., Apple Support, Mac User Guide, n.d. · 26 facts
- Voice dictation (Claude Code documentation)Anthropic, Anthropic, 2026 · 26 facts
- Type with your voice (Google Docs Editors Help), archived copy from December 2020Google Docs Editors Help (archived by the University of North Texas Web Archive), 2020 · 26 facts
- Voice Control commands to interact with your MacApple Support, Mac User Guide (macOS 27 version of the page), 2026 · 23 facts
- Dragon Professional 16.1 Release notesNuance Communications, Nuance Communications, Dragon Professional 16.1 help, n.d. · 20 facts
- openai/whisper: README (raw text)OpenAI, GitHub (openai/whisper), 2026 · 20 facts
- Voice access command listMicrosoft Support, 2026 · 19 facts
Government and public statistics
158 sources. The most used:
- Medical Transcriptionists: Occupational Outlook HandbookU.S. Bureau of Labor Statistics, 2025 · 20 facts
- Advertisement No. F.6/2024-SC (RC): Court Master (Shorthand), Senior Personal Assistant and Personal AssistantSupreme Court of India, 2024 · 14 facts
- Carpal tunnel syndromeNHS (National Health Service, England), 2024 · 9 facts
- 47 CFR 79.1: Closed captioning of televised video programming (captioning quality standards)US Federal Communications Commission, Code of Federal Regulations (text via Cornell Legal Information Institute), n.d. · 8 facts
- Disabled Students' AllowanceGOV.UK, 2026 · 8 facts
- Court Reporters and Simultaneous Captioners: Occupational Outlook HandbookU.S. Bureau of Labor Statistics, 2025 · 8 facts
- Repetitive strain injury (RSI)nidirect (Northern Ireland government), n.d. · 6 facts
- Typing Test Formula and IllustrationCentral Board of Secondary Education (India), n.d. · 6 facts
- Enforcement Guidance on Reasonable Accommodation and Undue Hardship under the ADAU.S. Equal Employment Opportunity Commission, 2002 · 6 facts
- Dictation handbook for primary English teachersHong Kong Education Bureau, Hong Kong Education Bureau, English Language Education, n.d. · 5 facts
Standard or regulation
25 sources. The most used:
- WebVTT: The Web Video Text Tracks Format (Editor's Draft)W3C Timed Text Working Group, W3C, 2026 · 6 facts
- Determining Threshold Level for Speech (ASHA Guidelines, 1988)American Speech-Language-Hearing Association, American Speech-Language-Hearing Association, 1988 · 6 facts
- Unicode Standard Annex #9: Unicode Bidirectional AlgorithmUnicode Consortium, Unicode Consortium, 2026 · 5 facts
- Web Speech API (W3C Community Group draft)W3C Web Speech API Community Group, 2026 · 5 facts
- Visible Black Character as the Unit of Text Measurement: AHIMA/MTIA Joint Task Force ReportAHIMA/MTIA Joint Task Force on Standards Development, American Health Information Management Association (AHIMA) and Medical Transcription Industry Association (MTIA), 2007 · 5 facts
- The Unicode Standard, Version 15.0, Chapter 12: South and Central AsiaUnicode Consortium, 2022 · 3 facts
- GNU General Public License version 3.0 (GPL-3.0)Free Software Foundation, Open Source Initiative, 2007 · 3 facts
- HTML Living Standard: Media elements, text track kinds (subtitles and captions)WHATWG, HTML Living Standard, n.d. · 2 facts
- Management of Carpal Tunnel Syndrome Evidence-Based Clinical Practice GuidelineAmerican Academy of Orthopaedic Surgeons, 2024 · 2 facts
- The Open Source DefinitionOpen Source Initiative, Open Source Initiative, 2024 · 1 facts
Dataset or benchmark
14 sources. The most used:
- api/SpeechRecognition.json (MDN browser-compat-data)MDN Web Docs (Mozilla), GitHub, 2026 · 5 facts
- Vectara Hallucination Leaderboard: LLM hallucination rates when summarizing a documentVectara, Vectara, GitHub, 2026 · 3 facts
- LibriSpeech ASR corpus (SLR12), Open Speech and Language ResourcesVassil Panayotov et al., Open Speech and Language Resources (OpenSLR), 2015 · 3 facts
- Medical Transcription Sample Reports & ExamplesMTSamples, 2026 · 2 facts
- GigaSpeech dataset card (speechcolab/gigaspeech)SpeechColab, Hugging Face, n.d. · 1 facts
- U+060C ARABIC COMMAcodepoints.net (Unicode character data), n.d. · 1 facts
- U+0964 DEVANAGARI DANDAcodepoints.net (Unicode character data), n.d. · 1 facts
- U+3002 IDEOGRAPHIC FULL STOPcodepoints.net (Unicode character data), n.d. · 1 facts
- VoxPopuli dataset card (facebook/voxpopuli)Meta AI, Hugging Face, n.d. · 1 facts
- Welcome to the AMI CorpusAMI Consortium, AMI Meeting Corpus, University of Edinburgh, n.d. · 1 facts
Survey or industry report
12 sources. The most used:
- Screen Reader User Survey #10 ResultsWebAIM, WebAIM (Web Accessibility In Mind), 2024 · 4 facts
- Communication in the Workplace: What Can NC State Students Expect?Jason Swarts et al., Professional Writing Program, Department of English, North Carolina State University, 2018 · 4 facts
- Oral Reading Fluency: Outcomes from 30 Years of Research (Technical Report 1701)Gerald Tindal, Behavioral Research and Teaching, University of Oregon, 2017 · 4 facts
- A Survey of Keystroke Dynamics BiometricsPin Shen Teh et al., PubMed Central, 2013 · 3 facts
- AI adoption among UK journalists and their newsrooms: surveying applications, approaches and attitudesReuters Institute for the Study of Journalism, Reuters Institute for the Study of Journalism, University of Oxford, 2025 · 2 facts
- Consumer Reports assessment of AI voice cloning productsConsumer Reports, Consumer Reports, 2025 · 2 facts
- Cost and Benefits of Accommodations (Workplace Accommodations: Low Cost, High Impact)Job Accommodation Network (AskJAN), 2025 · 2 facts
- Roughly 1 in 3 U.S. adults have a smart speaker; fewer have other smart home devicesPew Research Center, Pew Research Center, 2026 · 1 facts
- UK Smart Speaker Ownership Outpaces U.S.Edison Research, Edison Research (now SSRS), 2025 · 1 facts
- Stack Overflow Developer Survey 2022Stack Overflow, 2022 · 1 facts
Vendor page
229 sources. The most used:
- Home Assistant Voice Preview EditionHome Assistant project, Home Assistant, 2026 · 10 facts
- How to Format a Transcript: Everything There Is to KnowGoTranscript, GoTranscript, n.d. · 8 facts
- Freelance With Rev: Transcriptionist, Captioner, Subtitle Translator and Legal TranscriptionistRev, 2026 · 8 facts
- Wispr Flow pricing and plansWispr Flow, Wispr Flow (vendor website), 2026 · 8 facts
- An All-Neural On-Device Speech RecognizerJohan Schalkwyk, Google Research Blog, 2019 · 8 facts
- OpenAI API pricingOpenAI, OpenAI, 2026 · 7 facts
- Superwhisper: Free vs Pro features and licenseSuperwhisper, Superwhisper documentation, 2026 · 7 facts
- nvidia/parakeet-tdt-0.6b-v3 model card (Hugging Face)NVIDIA, Hugging Face, 2025 · 7 facts
- HIPAA Compliance & Healthcare Use (Wispr Flow Help Center)Wispr Flow Help Center, n.d. · 6 facts
- ElevenLabs API pricingElevenLabs, 2026 · 6 facts
Book
7 sources. The most used:
- Speech and Language Processing, Chapter 16: Automatic Speech Recognition (draft)Daniel Jurafsky and James H. Martin, Stanford University, online manuscript of the third edition, 2026 · 11 facts
- Home Education (Home Education Series, Volume 1)Charlotte M. Mason, Project Gutenberg, eBook 71087, 1886 · 10 facts
- Automatic Speech Recognition: A Brief History of the Technology DevelopmentB. H. Juang and Lawrence R. Rabiner, Elsevier Encyclopedia of Language and Linguistics (author copy, UC Santa Barbara), 2005 · 5 facts
- Henry James at WorkTheodora Bosanquet, Hogarth Press (Project Gutenberg edition), 1924 · 4 facts
- Speech and Language Processing (third edition, online draft)Daniel Jurafsky and James H. Martin, Stanford University, 2026 · 2 facts
- Crunching Big Data With Fingertips: How Typists Tune Their Performance Toward the Statistics of Natural LanguageLawrence P. Behmer Jr. and Matthew J. C. Crump, Big Data in Cognitive Science (Routledge), chapter 14, 2016 · 1 facts
- An AutobiographyAnthony Trollope, Project Gutenberg (ebook 5978, from the 1883 text), 1883 · 1 facts
News and journalism
120 sources. The most used:
- How accurate is Apple's new transcription AI? We tested it against Whisper and ParakeetMarcus Mendes, 9to5Mac, 2025 · 9 facts
- How to Try Out 26.10's Speech-to-Text App in Ubuntu 26.04 | 24.04UbuntuHandbook, 2026 · 5 facts
- 4 Fixes for “No Permission to Enable Voice Typing” on AndroidAnkita Sharma, Guiding Tech, 2024 · 5 facts
- Ready, Set, Type! Touch Typists Are Faster, But Not By MuchGordon D. Logan et al., Association for Psychological Science, summary of Logan, Ulrich and Lindsey (2016) in the Journal of Experimental Psychology: Human Perception and Performance, 2016 · 5 facts
- How the Dictaphone Entered Office LifeAllison Marsh, IEEE Spectrum, 2026 · 4 facts
- 5 Ways to Fix Voice-to-Text Not Working on AndroidGuiding Tech staff, Guiding Tech, 2024 · 4 facts
- How to set up Voice Message Transcription in Google MessagesDerrek Lee, Android Central, 2024 · 4 facts
- What Google Assistant features Gemini can and cannot accessAbner Li, 9to5Google, 2024 · 4 facts
- WhatsApp's Voice Message Transcript Feature Triggers Data Storage ConcernsMediaNama, MediaNama, 2024 · 4 facts
- Mac users burned after Nuance drops Dragon speech to text softwareThe Register, 2018 · 4 facts
Other
264 sources. The most used:
- openai/whisper: Robust Speech Recognition via Large-Scale Weak SupervisionOpenAI, GitHub (OpenAI repository), 2023 · 24 facts
- whisper.cpp READMEGeorgi Gerganov, GitHub, 2026 · 11 facts
- cjpais/Handy: a free, open source speech-to-text appCJ Pais, GitHub, 2026 · 10 facts
- Dvorak keyboard layout (Wikipedia)Wikipedia, 2026 · 10 facts
- QWERTY (Wikipedia)Wikipedia, 2026 · 9 facts
- Touch typingWikipedia, n.d. · 8 facts
- Announcing AA-WER Streaming (Artificial Analysis)Artificial Analysis, Artificial Analysis, 2026 · 8 facts
- ShorthandWikipedia, the free encyclopedia, n.d. · 7 facts
- Beingpax/VoiceInk: README (GitHub)GitHub (VoiceInk repository), 2026 · 7 facts
- whisper/tokenizer.py: the LANGUAGES table (openai/whisper)OpenAI, GitHub, openai/whisper, 2026 · 7 facts