Speechnotes
Speechnotes is an online speech-to-text platform for real-time voice typing, audio and video transcription, translation, captions, and automated transcription workflows.
Speechnotes is a browser-based dictation and transcription platform designed for writers, students, journalists, professionals, content creators, and businesses that want to convert speech into editable text. It provides two main workflows: a free online dictation notepad for voice typing in real time and a pay-as-you-go transcription service for recorded audio and video. The platform has served millions of users since 2015 and uses speech-recognition technology from Google and Microsoft.
The dictation notepad works directly in supported browsers without requiring registration or software installation. Users can alternate between speaking and keyboard editing, insert punctuation and formatting through voice commands, benefit from automatic capitalization, and save notes locally in their browser. Documents can be downloaded, printed, emailed, or exported to Google Drive. A Chrome extension also enables voice typing inside text fields on websites such as Gmail, with a floating microphone, keyboard shortcuts, and reusable text or emoji stamps.
For recorded material, Speechnotes can transcribe uploaded audio and video, YouTube content, Google Drive files, and other online sources. Results include automatic punctuation, timestamps, editable text, speaker diarization in English, AI summaries, translations, and subtitle generation. Transcripts can be exported as documents or caption files such as SRT and VTT.
Developers and businesses can automate transcription through a REST API, webhooks, and Zapier integrations. The service uses pay-as-you-go pricing rather than a transcription subscription, currently listed at $0.10 per minute. Free dictation is unlimited and ad-supported, while Premium removes advertisements and adds developer support. Speechnotes states that transcription recordings are automatically deleted after processing and that no human listens to uploaded media.