Practical overview
When it fits
Use Vivadicta when speech input, transcription cleanup or AI-assisted text processing needs to fit into a mobile writing workflow. Its note chat and semantic search address a separate task: retrieving information from existing transcripts and notes.
Who it is for
- People who want to dictate text into other apps using a voice keyboard.
- Users who need transcripts from recordings, including speaker-separated transcripts.
- People who want to search or ask questions about saved transcripts and notes.
Documented uses
- Dictate text into messaging, email and other apps, optionally processing it with AI.
- Transcribe speech with an on-device or cloud model and refine transcript formatting.
- Rewrite, summarize or translate selected text through the keyboard.
- Search notes by meaning and ask questions about one or multiple notes.
Requirements & limits
The repository links to an App Store listing. It identifies the project as MIT-licensed and lists Xcode 26+, iOS 18+, watchOS 10+ and Swift 6.2 for the project.
- Transcription can use on-device WhisperKit or Parakeet, or listed cloud providers.
- The project describes on-device RAG for note search and chat, while other AI processing can use Apple Foundation Models or cloud providers.
- The keyboard supports both dictation and AI processing of selected text in other apps.
- The repository identifies Swift as the implementation language and lists an MIT license.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Use VivaDicta’s keyboard for voice input
Transcribe speech into a text field in another app using the VivaDicta keyboard.
Before you start
- VivaDicta installed on an iPhone or iPad.
- VivaDicta’s custom keyboard enabled; consult the keyboard setup instructions for installation and Full Access details.
Steps
Open the app with the text field where you want to dictate and switch to the VivaDicta keyboard.
Tap the keyboard’s record button and speak.
Review the inserted text; VivaDicta can optionally process the transcription with AI before inserting it.
Expected outcome
Speech is transcribed and inserted at the text cursor, optionally after AI processing.
Guide limitations
- This guide does not provide the keyboard installation steps; see the keyboard setup instructions.
- AI processing is optional and the available transcription and AI settings depend on the configured pipeline.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 12 October 2026
- Original website title
- n0an/VivaDicta · Official homepage title · retained in its source language