Description
Dictate Anywhere You Type
Type 4x faster with your voice. Just speak, and AI turns your words into polished, ready-to-send text. Completely free.
WORKS EVERYWHERE YOU TYPE
One keyboard for all your apps. Dictate into Messages, WhatsApp, Email, Notion, or anywhere else - no app switching required. Your voice becomes text instantly. Swipe to switch between modes right from the keyboard.
AI THAT PROCESSES YOUR SPEECH
Raw transcriptions become polished text automatically. Powered by Apple Foundation Model right on your device - no setup, no cloud required. AI removes filler words, fixes punctuation, and formats everything perfectly. Use your clipboard or selected text as additional context - copy a message and dictate your reply.
KEYBOARD AI PROCESSING
Select text or place your cursor, then pick an AI preset - translate, rewrite, summarize, and more. Works in any app, right from the keyboard.
COMPLETELY FREE, NO EXCEPTIONS
No subscriptions, no paywalls, no limits. On-device AI, custom keyboard, unlimited transcriptions - all free.
PRIVATE BY DESIGN
Your voice never leaves your iPhone:
- All transcription runs on your device
- AI processing can run on-device with Apple Foundation Model
- Zero telemetry or tracking
- No accounts or sign-ups required
- Works in airplane mode
Cloud AI is optional and always under your control.
AI PRESETS
Process your text with 40+ built-in presets - rewrite, summarize, translate, and more. Create custom presets and mark favorites for quick access.
SPEAKER LABELS
Get speaker-separated transcripts for meetings, interviews, and group chats, so it's clear who said what.
VIVA MODES
Switch between AI-powered modes for different contexts. Each mode remembers its own AI settings. With Soniox, Gladia, or Speechmatics selected, your transcription can come back already translated in a single step.
LIVE TRANSLATION
Speak in one language and hear it back in another, in real time. Pick source and target, optionally play the translation through your headphones, and adjust playback speed. 60+ languages, any-to-any.
CHAT WITH YOUR NOTES
Ask questions about one note, many, or across your entire library. Surface insights, action items, and key points, with answers that show which notes they came from. Runs on-device with Apple Foundation Model, or with your favorite cloud AI.
SMART AI SEARCH
Find notes by meaning, not just keywords. Ask "what did I say about the pricing idea?" and VivaDicta finds it - even without those exact words. Fully on-device.
REMINDER SUGGESTIONS
Turn notes into reminders, in the original language of your note. Review suggestions and send approved items straight to Apple Reminders.
APPLE WATCH APP
Record voice notes right from your wrist. Tap and talk - your notes are sent to iPhone and transcribed in the background.
FULLY CUSTOMIZABLE
- 16 AI transcription providers (local and cloud)
- 25 AI processing providers
- Bring your own AI via any compatible API
- Personal dictionary, word replacements, and custom tags
- Save transcriptions to Obsidian automatically
- Auto export to a folder of your choice
KEY FEATURES
- System-wide Voice keyboard with AI text processing
- On-device Whisper and NVIDIA Parakeet - professional-grade transcription
- Live Translation - real-time speech-to-speech across 60+ languages
- Chat with AI about one note or many, with Smart AI Search
- On-device Apple Foundation Model, or connect your own cloud AI
- Reminder suggestions sent to Apple Reminders
- iCloud sync across iPhone, Apple Watch, and Mac
- Home screen widgets and Siri Shortcuts integration
- Multi-language keyboard: French, German, Spanish, Russian
- 100+ languages with auto-detection
- Open source on GitHub
PERFECT FOR
- Quick messages and emails
- Meeting notes and lectures
- Voice memos and ideas
- Journalists and writers
- Developers and students
- Anyone who thinks faster than they type
Download VivaDicta.
Your voice. Your words. Your device. Your privacy.
Nouveautés (v3.5.0)
More ways to transcribe, process, and personalize.
VivaDicta 3.5.0 adds AssemblyAI as a new cloud transcription provider, two new AI processing providers (Ollama Cloud and MiniMax), and a new Recording Orb picker so the recording screen looks the way you like. Plus performance and polish.
AssemblyAI Transcription
A new cloud transcription provider with high accuracy, speaker labels, and broad language support. Add your AssemblyAI API key in Settings > AI Settings > Transcription to try it.
Ollama Cloud
Run Ollama's hosted AI models without running your own server. Add an API key from ollama.com and pick a model in your mode's AI settings. Separate from the existing local Ollama option, and the model list refreshes automatically once your key is added.
MiniMax AI
A new AI processing provider for cleaning up and rewriting your transcriptions. Add your MiniMax API key in Settings and choose any of its M-series models.
Recording Orb
Pick the visualization shown while you record: Particles, ASCII, or None. The orb is also lighter and smoother now, so it won't bog down on busy devices.
Quality of Life
The app version and build now show at the bottom of Settings, the recording orb uses far less power, and a round of polish across the app.