Available now · macOS 14+ · Apple Silicon

Talk to your agents.
They use their tools.
The work gets done.

Super Voice Mode puts a voice interface in front of Codex, Claude, Cursor, OpenCode, Ollama, and local agents on your Mac. They keep their native tools, working context, and workflows. Dictation in every app stays free and runs on-device by default.

Works with
Codex Claude OpenCode Ollama Hermes
native agent tools persistent context free local dictation
Ready
Ready
You
hold ⌥⇧ and speak…
Assistant
·

A productivity tool.
Not a pretend human.

Your AI will cheer for your worst ideas. Apologize for things it didn't do. Pretend to care. We've all learned to ignore it. We're building something better, a tool that helps you get stuff done, stays honest about what it is, and keeps the quirks in on purpose.

Your voice. Your character. Your choice.

Speak naturally.
Get text that looks written.

on-device
BEFOREwhat the mic heard
so um import the num pie library and create a data frame from the csv
AFTERwhat Super Voice Mode types
import numpy as np
import pandas as pd

df = pd.read_csv("file.csv")
← drag or wait
the shortcut

One key. Any app.

Hold Right Option anywhere on your Mac. Text lands at your cursor. Slack, Gmail, Cursor, Xcode, Terminal, browsers, Obsidian. If you can type there, you can dictate there.

Slack Gmail Xcode Cursor Obsidian Terminal Browsers
hold Right Option
speak
cursor
paste

Dictation

Hold Right Option, speak, release. Clean text appears wherever your cursor is.

AI Writing

Ask what you want written. With highlighted text, Right Option can talk to AI instead of replacing. Free.

Live Transcription

Double-tap the dictation key for longer hands-free sessions with live subtitles. Pro.

Your agents. Their native tools.
Voice becomes the control layer.

Super Voice Mode drives the agent tools you already use instead of replacing them with a generic chatbot. Speak the outcome you want, follow the work as it happens, and continue the same session without rebuilding context.

Listening
on-device, no cloud
Thinking
your AI model
Speaking
character voice
03 Meetings local capture

Meeting notes that become memory.

Capture the room and the call without inviting a bot. Super Voice Mode saves notes, transcripts, decisions, and action items to a local markdown vault your assistant can search later.

Explore Meetings → bot-free · file-backed · local-first
Meetings · Customer sync
capturing
Local room mic
Meet app audio
meeting_notes.md
## Customer sync
## Decisions
• Start with ten seats
• Keep transcript local
## Action items
• Send SSO checklist
• Confirm pilot group
04 Slate new

A canvas for the conversation.
Beyond chat.

Voice forgets. Chat is slow. Slate is the missing middle: a shared document that takes shape while you talk. Press ⌘⇧S, speak, watch it write.

Explore Slate → human-AI collaboration · in active development
⌘⇧S Slate
writing
draft a q3 plan
"On it."
split risks…
## Q3 plan
## Risks
• Infra: cold-start latency
• Vendor: LLM lock-in
## Wins
• Slate ships
• Validated with first 50 users

Select. Speak. Transform.

live on any text field
draft.md
## Notes · draft
 
A few things from this morning's sync:
 
we should probably think about maybe adding a feature that lets users export their data in some kind of format
 
Follow-ups: schedule review, loop in design.
IDLEMake this better
Rewrite selection
or just speak a command
pressanywhere

Meet Iris.
An assistant with a name.

shipping today
🌟
Iris
your AI

"Copy that, one moment."

direct dry humor volunteers context calls you "Boss"

Every assistant out there is a faceless chatbot. Iris is your AI: a voice, a name, opinions, and a personality that shows up the same way every time you hit the hotkey.

Iris is the anchor. Stack a persona on top to shift the voice without losing the character.

See Iris with personas ↓

Iris, filtered.
Same assistant, different voice.

30+ bundled · mix & match
Character
shipping
+
Persona
youGive me a status update on the deploy.
Iris · Drill Sergeant

Switch characters up top. Swap personas to change how they sound.

Zero bytes to the cloud.
Not a feature. The foundation.

1,247
dictation sessions today
0
bytes sent to any server
100%
processed on your machine

Speech-to-text runs on your machine. Correction runs locally. When you use the assistant, your AI service handles the request. We never see it. Audio never leaves the machine.

data path

Clear boundaries. No guessing.

local-first by design
Dictation audio
Stays on your Mac

Captured, transcribed, and discarded locally.

AI correction
Stays on your Mac

The cleanup model runs locally through MLX.

Assistant requests
Your chosen backend

Sent only when you ask Claude, Codex, OpenCode, Ollama, Hermes, or a local model to act.

Super Voice Mode servers
Never receive content

No account, no telemetry, no hosted transcript store.

01

Hold & speak

Right Option anywhere on your Mac. Text lands at your cursor.

02

On-device transcription

State-of-the-art speech-to-text. Runs privately on your machine.

03

Meetings

Capture calls, notes, transcripts, and action items in a local markdown vault.

04

Bring your own AI

Route to any advanced model. Cloud or local. Your keys, your data.

05

Character voices

Spoken assistant responses, on-device. Hands-free.

06

30+ personas

Stack up to two. Some useful, most hilarious.

ready?

Hold a key. Ship faster.

macOS 14 or later. No account, no telemetry.