Private · On-Device · No Cloud

Private AI That Runs Entirely On Your Device.

Whisper runs powerful language models fully on your device. No servers, no accounts, no tracking. Talk to it hands free, show it images, and let it act on your phone: calendar, alarms, contacts, messages. Offline by default. Everything stays yours.

Download for AndroidFree APK · Android 8.0+ · Not on the Play Store yet
9:41
Whisper
Qwen3 4B · tools · offline
Models
What's on my calendar today?
Read calendar
Three events — Design review at 11:00, lunch with Sam at 12:30, and a 1:1 with Priya at 3:00 pm. Want me to nudge you ten minutes before each?
yes, 10 min before each
Ask anything…Send

Runs the open models you already love

  • QwenQwen
  • GemmaGemma
  • MetaLlama
  • AzurePhi
  • HuggingFaceSmolLM3
The agent

It doesn't just answer. It acts.

Ask for something and a small model running on your own phone picks one of 18 tools wired into Android, fills in the arguments, and runs it.

  • Calendar & time

    4 tools

    Reads your schedule, and books into it when you say so.

  • People & messages

    4 tools

    Finds the contact, drafts the message, hands you the send button.

  • Web

    4 tools

    The one place it reaches outside your phone, and only on request.

  • Your device

    6 tools

    The small things you would otherwise dig through settings for.

Anything that creates something on your phone stops and asks for a tap first. Everything else is a read, and reads never leave the device.

All 18 tools by name
  • list_calendar_events
  • create_calendar_event
  • schedule_reminder
  • set_alarm
  • search_contacts
  • dial_number
  • compose_sms
  • compose_email
  • web_search
  • web_fetch
  • open_url
  • open_maps
  • get_location
  • get_battery
  • read_clipboard
  • write_clipboard
  • set_brightness
  • search_phone_media
Search your contacts
search_contacts
Draft a text
compose_sms
Open the dialer
dial_number
Draft an email
compose_email
On-device model
runs on your phone
waiting

Ask for something…

Live voice

Talk to it. Hands free.

Open Live and just speak. Whisper listens, works out when you have finished, answers out loud, and reopens the mic. The whole loop runs in airplane mode, with nothing streaming anywhere.

  1. 01It hears you stop

    Voice-activity detection watches the mic level and ends your turn on a second of silence. No wake word, no push-to-talk.

  2. 02It transcribes, on device

    whisper.cpp turns the audio into text right on the phone. The recording never becomes a file that leaves it.

  3. 03It thinks, on device

    The same local model you picked answers, and can reach for any of the 18 tools while it does.

  4. 04It speaks back

    Kokoro-82M synthesizes the reply through sherpa-onnx, then the loop reopens the mic for your next sentence.

Listening…

Eight voices to answer in

Preview each one in Settings and keep the one you like. Every voice is synthesized on the phone.

  • Ariadefault
  • Bella
  • Nicole
  • Michael
  • Fenrir
  • Puck
  • Emma
  • George
How it decides

You can watch it think.

Small models are the ones most likely to claim they did something they didn't. Whisper is built so that claim is structurally impossible, and so you can check it yourself.

It cannot fake success

Every planning turn is forced through a grammar that only accepts a real decision: call this tool with these arguments, or answer. A model that would otherwise reply “I've set your alarm!” without setting one literally cannot emit that.

Decisions aren't rolled for

Planning is decoded greedily at temperature zero, because it is control flow, not prose. Only the sentence you actually read is sampled, so the choice to act doesn't change from one run to the next.

You can read the log

Turn on the trace and every decision, tool call, argument and result is recorded step by step, raw model output included, with an export button. Nothing about the loop is hidden from you.

Agent trace
running0 entries
You said

    0 tool calls · temp 0 · grammar-constrained
    The library

    Nine models. Or bring your own.

    Download, switch and delete models inside the app. Whisper reads your phone's actual RAM and free storage first, and warns you before you pull something that would get killed by the OS.

    Qwen

    Qwen3 4B Instruct

    Strongest at phone actions. The one to pick for the assistant.

    2.3 GB6 GB+tools
    Gemma

    Gemma 4 E2B

    Multimodal. The one that can look at your screenshots and photos.

    3.4 GB6 GB+vision
    Meta

    Llama 3.2 3B Instruct

    Meta's compact chat model. Fast, friendly, reliable for everyday questions.

    1.9 GB6 GB+tools
    Azure

    Phi-4 Mini Instruct

    Microsoft's small model. Strong at math, logic and structured answers.

    2.3 GB6 GB+tools
    HuggingFace

    SmolLM3 3B

    Fully open, reasons step by step. A good balance of speed and smarts.

    1.8 GB6 GB+tools
    Qwen

    Qwen3 1.7B

    Smallest and fastest, and it shows its thinking. For older phones.

    1.0 GB4 GB+tools
    Qwen

    Qwen3 1.7B · Uncensored

    Refusal removed at the weights, not prompted around. For older phones.

    1.0 GB4 GB+toolsabliterated
    Qwen

    Qwen3 4B · Heretic

    Optimised abliteration: refusals gone, the model otherwise unchanged.

    2.5 GB6 GB+heretic
    Gemma

    Gemma 4 E4B

    The bigger sibling. Needs a 12 GB device, and the app will tell you.

    6.0 GB12 GB+vision

    Any GGUF on Hugging Face works

    Paste a direct model URL on the Models screen and it downloads like any built-in one, progress bar and all. Add the matching mmproj file and that model gets vision too. The catalog is a starting point, not a walled garden.

    Privacy

    No servers, because there is no backend.

    Whisper has no accounts, no analytics, no telemetry and nothing to sign in to. There is no server to send your data to even if someone wanted to. Here is the exact line, in both directions.

    Passes the airplane test

    Switch the radios off and everything still works: the chat, the voice loop, the calendar, the alarms. That is the whole proof, and you can run it yourself.

    Airplane mode
    what's on tomorrow?
    Three events. First is standup at 9:30.
    answered offline

    No server on the other end

    There is no Whisper backend. Nothing to breach, nothing to subpoena, nothing that goes down. Your phone talks to itself.

    your phone
    no server
    0 endpoints0 API keys0 accounts

    Nothing to sign in to

    No account, no email, no phone number. Install it, pick a model, start talking. There is no profile of you anywhere because none is ever created.

    Email
    Password
    Sign in
    no account created

    No analytics, no telemetry

    No usage tracking, no crash reporter, no advertising ID. There is no analytics SDK in the app, so there is nothing to opt out of.

    Outbound today0 requests
    • Analytics SDKnot included
    • Crash reportingnot included
    • Advertising IDnot included
    • Session replaynot included

    Your data stays where it is made

    Every message, recording, transcript, contact lookup and calendar read lives on the phone, along with the models and the full agent trace.

    • Messages
    • Voice
    • Contacts
    • Calendar
    • Location
    • Photos
    • Models
    • Trace
    stays here

    Leaves only when you ask

    Exactly three things ever go out, each behind your own tap, and nothing else rides along with them.

    • A web search query
      only the query, when you ask
      you tap
    • A page URL to fetch
      when you ask it to read one
      you tap
    • A model download
      once, from Hugging Face
      you tap
    Questions

    Before you download

    Does it really work with no internet?

    Yes. Once a model is downloaded, chat, live voice, calendar, alarms, contacts and the rest run in airplane mode. The only two tools that need a connection are web search and page fetch, and they only run when your request needs them.

    Why isn't it on the Play Store?

    It is not listed yet. For now it is a free APK you install directly, and Android will ask you to allow installs from your browser the first time. Nothing about the app changes when it does reach the store.

    Which model should I start with?

    Qwen3 4B Instruct if you want the assistant that actually does things on your phone, since it is the strongest of the small models at picking tools. Gemma 4 E2B if you mostly want to show it images. On a 4 GB phone, start with Qwen3 1.7B.

    How fast is it?

    Honestly: a 2-4B model on a phone CPU is usable, not instant. Expect a short wait for a reply, longer on older hardware. Smaller models are noticeably quicker, which is why the library spans 1 GB to 6 GB rather than shipping one size.

    Will it fill up my phone?

    Models are between 1 GB and 6 GB and none of them ship inside the app, so you choose what to download and can delete any of them from the Models screen. Whisper shows your free storage and RAM before you start a download, and warns you if a model would not fit.

    Can I run a model that isn't in the list?

    Paste any direct GGUF URL from Hugging Face on the Models screen and it downloads like a built-in one. Add the matching mmproj file alongside it and that model gets vision as well.

    Is there an iPhone version?

    Not yet. Android is first; the codebase is Expo and already builds for iOS, so it follows once the assistant is proven on Android.

    Your assistant, on your phone, and nowhere else.

    Free, no account, no sign-in. Install it, pick a model, and put the phone in airplane mode to see for yourself.

    Download for AndroidFree APK · Android 8.0+ · Not on the Play Store yet