Google has launched a new AI-powered dictation app called Google AI Edge Eloquent. The app focuses on offline speech-to-text and is currently available on iOS. According to Google, the dictation app converts speech to text in real time and can work offline after downloading models, using Google’s Gemma AI for speech recognition. With this release, Google is entering the growing space of AI transcription tools that turn spoken words into clean, usable text.
What is Google AI Edge Eloquent
As per the app’s listing on the App Store, Google AI Edge Eloquent is an “advanced dictation app engineered to bridge the gap between natural speech and professional, ready-to-use text.”
It further added that, “unlike standard dictation software that transcribes stumbles and filler words verbatim, Eloquent uses AI to capture your intended meaning. It automatically edits out ‘ums’, ‘uhs’ and mid-sentence self-corrections, outputting clean, accurate prose.”
Google AI Edge Eloquent is a dictation app that converts speech into text in real time. Once users download the required models, the app can work without an internet connection. It is based on Google’s Gemma AI models for automatic speech recognition. The app shows live transcription as you speak. When you pause, it automatically cleans up the text by removing filler words like “um” and “ah”, and makes the output more readable.
Users can switch off cloud mode to rely only on on-device processing. When cloud mode is enabled, the app uses Gemini models for refining text. It can also pull in keywords, names and jargon from Gmail if needed, and lets users add their own custom words.
The app displays the history of the transcription session and lets you search through all of them as well. It can show you words dictated in the last session, your words-per-minute speed and the total number of words spoken.
Key features of the app
The app includes several tools to improve and customise text:
-
Live transcription with offline support -
Automatic removal of filler words -
Text formatting options like “Key points”, “Formal”, “Short” and “Long” -
Option to switch between local processing and cloud-based processing -
Ability to add custom words, names and jargon
Availability and plans
As of now, the app is only available on iOS. However, the App Store listing mentions an upcoming Android version. The app currently requires iPhones running iOS 16 or later. It also supports Macs with macOS 13 or newer and Apple silicon (M1 chip or later), as well as Apple Vision devices running visionOS 1.0 or above.
