Your voice, unleashed.
What if you could type into any app, just by speaking —
IfVoice is an AI voice input interface for macOS. Press a hotkey, speak, and your words become text.
Local by default.
Speech recognition stays on your Mac. Cloud LLM features are optional — and only when you choose them.
On-Device Recognition
Default speech recognition runs on-device for fast inference. Works offline, and audio is processed on your Mac.
Context-AwarePro
When LLM text formatting is enabled, style adapts to the active app — formal in Mail, casual in Slack, code in VS Code.
Fast Response
By default, see a live preview while recording. Final text is inserted at the cursor when you stop.
Auto Meeting Minutes
Dual recording of mic + system audio with speaker diarization, summaries, and Markdown export.
Multilingual (Engine Switch)
Japanese-first by default. Switch to a Whisper-family engine for English, Chinese, Korean, French, and more — 12 languages in total.
Custom Hotkeys
Trigger with your preferred key combination. Supports push-to-talk and toggle; toggle is the default.
Simple as 1-2-3
Install and start speaking immediately.
Press the Hotkey
Press your configured hotkey in any app to start recording.
Speak
Just talk into your microphone. By default, a live preview appears while you record.
Text Auto-Inserts
When you stop recording, text is inserted at the cursor.
Different app, different voice.
With LLM text formatting enabled, the same speech can be formatted for each context.
"The meeting tomorrow has been moved to 3 PM. Please notify all participants."
Dear team,
Please be advised that tomorrow's meeting has been rescheduled to 3:00 PM.
Kindly notify all participants at your earliest convenience.
Best regards
// TODO: Meeting rescheduled to 15:00 tomorrow // - Notify all participants
The meeting tomorrow has been moved to 3 PM. Please notify all participants.
Your voice belongs to you.
IfVoice is designed privacy-first from the ground up.
Local by Default
By default, speech recognition runs on-device and audio is not sent to our servers.
Cloud is Opt-In
Cloud LLM features such as text formatting and meeting summaries are optional. Use your own API keys (BYOK). Separate network traffic may occur for license or trial validation.
Transparency Promise
We explain how the service works and handles data as clearly as possible.
Free your meetings from note-taking.
Dual recording and AI summaries automate your meeting minutes.
Dual Recording
Captures both mic and system audio simultaneously
Speaker Diarization
Automatically identifies and labels speakers
Markdown Export
Exports structured minutes
AI Summary
Auto-summarizes key meeting points
Find your plan.
On first launch, eligible devices can start a 7-day in-app free trial (connecting to the license server may be required). Try before you decide.
Pro One-Time
All features, pay once
- Local speech recognition (switchable multilingual engines)
- Custom hotkeys
- LLM text formatting (BYOK)
- Context-aware text formatting
- Unlimited meetings (90 min)
- Meeting summaries & export
- Large STT models
Updates released after day 180 are not included
Buy with StripePro Subscription
Always up-to-date + future cloud features
- Local speech recognition (switchable multilingual engines)
- Custom hotkeys
- LLM text formatting (BYOK)
- Context-aware text formatting
- Unlimited meetings (90 min)
- Meeting summaries & export
- Large STT models
- Update guarantee
Cloud integration planned for future releases
Buy with Stripe- Non-refundable
- Apple Silicon only (Intel Macs are not supported)
- One-time plan: no update guarantee after 180 days
- 7-day trial is in-app
- No iPhone or iPad version
Start typing with your voice.
Requires macOS 13.0 (Ventura) or later
There is no iPhone or iPad version. Requires macOS 13.0 (Ventura) or later on Apple Silicon (M1 or later).