Preview
Description
Corvin turns speech into text straight from your keyboard — and never sends your voice anywhere. Tap the microphone on the Corvin keyboard, speak, and the text lands in whatever field you were typing in: a messenger, notes, mail, a search box. Recognition runs on the device itself using Whisper models. Neither the audio nor the transcripts go anywhere: the keyboard and the app talk to each other inside your phone. FEATURES • Dictate in any app — Corvin works as an ordinary keyboard • Fully on-device: once a model is downloaded, no internet is needed • Choose your model, from a light 75 MB one to the most accurate at 3 GB • Over 90 languages • Searchable transcript history, with optional auto-cleanup • Transcribe existing audio files: OGG (Telegram voice messages), WAV, M4A, MP3, AIFF PRIVACY Corvin has no analytics, no trackers and no accounts, and collects nothing about what you type. The keyboard's Full Access is used only to reach the Corvin app inside your device — never to collect keystrokes. MODELS Models are downloaded only when you pick one; nothing pulls gigabytes without asking. Start with the small model: 466 MB, and solid on everyday speech.
What's New
Version 1.5.7 2026-10-18
New recognition model for Russian: Sber's GigaAM v3, with punctuation and numbers as digits. Dictation dictionary: add names and terms, and Corvin will recogniz... Technical Analysis
Package Overview Basic metadata
Bundle ID
com.corvinvoice.ios Current Version 1.5.7
Minimum iOS 16.0
Package Size App Store Size
Package Metadata 0 / 0 version records
Detailed binary, privacy manifest, framework, and Info.plist results have not been indexed for this package yet. The verified App Store and archive metadata above remains available.
Developer Information
Known Version Records
0 version records with stored package metadata
Stored metadata does not guarantee a package is currently available to download.
| Details | Version / IDs | Version date | Action |
|---|