Google Voice Access vs Voice In

Google Voice Access lets people control an Android device by speaking, including people who have difficulty manipulating a touchscreen. It can open apps, go back or home, show notifications and operate the screen currently in use. Users can display numbers or text labels beside screen items and speak the matching marker to select one. Voice Access also supports dictation and text editing, including replacing words or phrases. Google lists English, Spanish, German, Italian, French, Portuguese and Japanese; Portuguese and Japanese cover only the top 25 commands. Offline use requires downloading a speech-recognition language pack to the device. Speech is mainly processed on-device, but audio may be sent to Google servers depending on device settings and system language; Google says audio sent for this service is not saved. Audio and transcripts are not stored unless the user enables “Help improve Voice Access Commands.” The microphone listens while Voice Access is active. It does not identify a particular speaker, so anyone can control an awake, unlocked device while it is listening.

Voice In is a browser extension that turns speech into text in web text fields, placing recognized words at the cursor in real time. It is available for Chrome and Edge on Windows, macOS, Linux, and Chromebooks, and supports more than 50 languages and 100 dialects. Built-in voice commands can add punctuation or paragraphs and correct common dictation errors. The maker says it supports more than 10,000 websites and lists 268 tested apps; some listed apps require Plus Advanced Mode. The free plan provides 60 minutes of dictation per day. Voice In Plus adds unlimited dictation, Advanced Mode, custom voice commands, a Dictation Box, language switching, case changes, and premium support. AI Transforms can polish selected text or apply a customized style; the maker says only selected text is sent to an AI model and is not stored by Voice In. Dictation requires an active internet connection and does not work offline. Its privacy policy says dictated audio and transcript text are processed using browser speech-to-text and are not sent to Voice In servers.