about 18× real time
Transcription finishes before you do.
Two-way voice. Real work. Run your AI agents
Run your AI agents
like a team.
Talk naturally. Ginu delegates work to your agents and keeps track of everything they're doing,
and brings you in only when your judgment is needed.
Local speech. Memory in your own files. The Claude Code, Codex or Gemini account you have.
macOS · Windows · Linux iOS · Android
Why voiceAgents got autonomous.
Agents got autonomous.
I didn’t get faster at typing.
When several agents are working at once, the scarce resource is not compute, it is your attention. Every time you stop to read a terminal you pay a context switch, and the agents wait for you at exactly the point where you are slowest.
Read why interruptions work differently
Saying “spawn someone to chase that flaky test, and show me the auth diff when it’s ready” takes three seconds and no context switch. Ginu runs both. The harder half is the other direction, and it is the part I actually built: it stops interrupting you while you are thinking. A routine completion waits for a gap in the conversation. A worker that has been blocked on you for three minutes earns the right to interrupt. Something irreversible does the opposite of shouting — it waits for a genuine break and is framed slowly, because a decision you cannot undo must never arrive as a yes-or-no that a reflexive “yeah” could approve.
You can believe that because none of it is a notification setting. Every piece of news is scored against the room — whether a turn is in flight, whether Ginu is already speaking, whether you are mid-sentence, how long it has been quiet — by a policy that is a file you can read. An agent cannot mark its own news urgent: it reports facts, and the policy turns facts into a number, which is the only reason everything here isn’t P1. And every decision it made is a line in a log with the evidence it had.
A conversation that keeps up.
Measured in real sessions.about 4× real time
The first sentence is spoken while the rest arrives.
43 ms
Speech can be stopped mid-word.
Playback block size, not end-to-end interruption latency.
None.
Your voice stays off speech servers.
See the full measurements
| What was measured, and how | Value |
|---|---|
| Transcription throughput against real-time audio: warm, timed in a real session on an M-series Mac. | about 18× real time |
| Speech synthesis throughput: warm, timed in a real session on an M-series Mac. | about 4× real time |
| Playback block size, 43 ms; a cut-in stops playback at the next block. This does not measure recognition or end-to-end interruption latency. | 43 ms |
| Time to the first agent response in per-turn timing logs, measured with Claude Code. Includes provider latency; it is not a local speech-processing figure. | about 3 s |
| Cloud round trips for speech, by architecture | none |
Measured on an M-series Mac. Yours will differ with hardware; the same timing line is written to your transcript on every turn.
Keep the whole pictureWork carries on.
See how tasks work
Work carries on.
Your attention
stays yours.
File the next few things. The board shows what is running, what finished, and the one card that is blocked on an answer from you.
Read more
Queued tasks are records on disk, so they are still there after a restart. A high-priority one starts the moment you file it, and nothing already running is paused to make room.
One decision needs you. The rest keeps moving.
2 running1 needs you1 ready
An illustrated example using Ginu’s task states.
Built around youSix things it does.
Pick one to see how it works. Six things it does.
None of them typing.
ConversationInterrupt it mid-sentence.
DelegationSend the work somewhere else.
OvernightFile the work, then leave.
Your sayNothing irreversible happens quietly.
Your memoryIt remembers, in files you can read.
From your phoneTake the session with you.
01 / 06 · Illustrated example
One session, microphone open throughout.
Ginu keeps listening while it speaks, so cutting in is just talking. It stops, hears you, and answers the new thing.
Read more
A short “mm” or “yeah” is read as backchannel and does not stop it. Words do.
Try sayingExplore conversation“Wait—check the audio test first.”
02 / 06 · Illustrated example
Each agent in its own copy of the code.
A delegated task is a separate process on its own git branch and worktree. Nothing it does reaches your working tree until you accept it.
Read more
Open its live terminal to watch the real process, and type into it to redirect the work mid-run.
Try sayingExplore delegation“Look into that failing audio test while I work on the design.”
03 / 06 · Illustrated example
A queue that outlives the session.
Queued tasks are records on disk, not lines in a chat. They survive a restart, each with its result and whether its branch merged.
Read more
A high-priority agent task starts the moment it is filed. Nothing already running is paused for it.
Try sayingExplore overnight“Work through these tasks and tell me what needs my attention.”
04 / 06 · Illustrated example
Every ask in one place, waiting.
Permission asks and irreversible actions collect behind the bell instead of scrolling past. They wait: nothing here times out.
Read more
An agent cannot mark its own news urgent. It reports facts; a policy you can read turns them into a priority.
Try sayingExplore your say“Show me the changes before publishing anything.”
05 / 06 · Illustrated example
Memory you inspect and correct.
What Ginu learns about your work is a tree of notes on your own disk, each one keeping the belief it replaced.
Read more
A guess is labelled assumed until you confirm it, and correcting one is a sentence: “that’s wrong, it’s pnpm”.
Try sayingExplore your memory“What did we decide about this project last time?”
06 / 06 · Illustrated example
A paired phone, for as long as you set.
Open a pairing window on your computer, scan it with any phone, and the same conversation and tasks appear in its browser. Your computer still does the work.
Try sayingExplore from your phone“How are the tasks going? Is anything waiting for me?”
Personal should mean yoursYour voice stays close.
Your voice stays close.
Your context stays with you.
Speech is recognised and spoken on your computer, so no audio is sent anywhere. Memory is a tree of notes in files you own, ready to read and correct.
What still leaves your computer
The text does. Your chosen CLI sends the transcribed turn and the context it needs to its own provider — Claude Code to Anthropic, Codex to OpenAI, Gemini to Google. Ginu has no server in that path.
Start with one useful conversationWhat would you
What would you
like to get done?
Bring a real project. The first conversation is worth more than the first demo.
It's a closed beta, and it's free.