Native recording & live waveform
High-fidelity capture via the Rust-native CPAL library, with a sleek floating overlay. Voice Activity Detection ends the take and starts transcribing the moment you stop speaking.
Speak.
The rest is text.
Simplevoice is a privacy-first, fully offline speech-to-text app for the desktop. Press a key, talk, and your words land in any app — no cloud, no account, no telemetry.
Available for macOS Windows Linux
★ Demo
See Simplevoice in action.
From a single keystroke to finished text — a full dictation, running entirely on-device.
01 How it works
Three keys to finished text.
No setup ritual. No dashboard to learn. The whole loop takes a single keystroke — speak, and it's written.
01
Press the hotkey
Hit Ctrl / Cmd + Shift + Space from any app. A floating overlay appears and starts listening — wherever you are.
02
Speak naturally
Talk at your own pace. Voice Activity Detection notices when you stop and transcribes on-device, automatically.
03
Text lands where you type
Your words are auto-pasted straight into the active field — or copied to the clipboard with a second hotkey.
02 Features
Everything you need to dictate, nothing you don't.
A focused tool that does one job exceptionally well — capture your voice and turn it into finished text, wherever you work.
Local & offline recognition
Multiple ASR backends run entirely on your machine, with hardware acceleration and a safe CPU fallback.
Metal · macOS Vulkan · Linux / Windows CPU fallback
Cloud, on your terms
Optional bring-your-own-key transcription. Keys are stored only in the OS keyring — never on disk.
Shortcuts & auto-paste
A global hotkey records from anywhere; your dictation is typed into the active field — including pure-Rust injection on Wayland.
Built-in model manager
Browse and download recommended models in-app with live progress, or import your own.
History & usage analytics — stored on your device
A full local history of transcriptions, durations and word counts in SQLite, with totals and 7-day / 30-day / all-time charts. Nothing leaves your machine.
Last 7 days
Example
03 Engines
Four local engines. Or bring your own key.
Choose the engine that fits your hardware and the model you want — all running locally — or route to a cloud provider with your own API key.
Local · runs offline on-device
Whisper.cpp
whisper-rs- Models
- Whisper GGML / GGUF (tiny → large)
- Acceleration
- Metal · Vulkan
Candle
candle- Models
- Whisper, Wav2Vec2 / CTC (Hubert, WavLM)
- Acceleration
- CPU · Metal
sherpa-ONNX
ort- Models
- Parakeet TDT v3 (INT8), Moonshine
- Acceleration
- CPU
NeMo
experimental- Models
- FastConformer-CTC, Conformer-RNN-T
- Acceleration
- Python sidecar
Cloud · bring your own key
OpenAI
- Default model
- whisper-1
- Endpoint
- api.openai.com
OpenRouter
- Default model
- openai/whisper-large-v3
- Endpoint
- openrouter.ai
Google Gemini
- Default model
- gemini-1.5-flash
- Endpoint
- generativelanguage.googleapis.com
Custom
- Default model
- your choice
- Endpoint
- any OpenAI-compatible URL
Anthropic Claude is intentionally not offered for transcription — Claude does not support audio input.
04 Privacy
Your voice never leaves your machine.
Simplevoice is private by architecture, not by policy. Recognition runs fully on-device — nothing is sent anywhere unless you explicitly choose a cloud engine.
Offline by default
With a local engine, your audio is transcribed entirely on your device. No internet required.
-
Zero telemetry
No analytics, no tracking, no phone-home. There is nothing to opt out of, because we collect nothing.
-
No account, ever
No sign-up, no login, no profile. Install it and start talking — you stay anonymous.
-
Keys in the OS keyring
If you opt into a cloud engine, API keys live only in your operating system's keyring — never on disk or in localStorage.
-
Open source, Apache-2.0
Every line is inspectable and auditable on GitHub. Trust the code, don't just take our word for it.
05 Download
Get Simplevoice for your desktop.
Free and open source. Pick your platform and architecture — every build lives on GitHub Releases.
Linux
Windows
Prefer to compile it yourself? Build from source ↗
06 FAQ
Questions, answered.
Everything worth knowing before you start talking.
Is Simplevoice really free and open source?
Yes. Simplevoice is licensed under Apache-2.0 and the full source lives on GitHub. There are no paid tiers and no accounts.
Does it work completely offline?
Yes. With a local engine — Whisper.cpp, Candle, sherpa-ONNX / Parakeet, or NeMo — transcription runs entirely on your device, with no internet connection required.
Do you collect any data or telemetry?
No. Zero telemetry, no analytics, no phone-home. Your transcriptions, audio, and usage stats stay on your machine, stored locally in SQLite.
Where are my cloud API keys stored?
If you opt into a cloud engine (bring your own key), API keys are stored only in your operating system's keyring — never on disk or in localStorage.
Which platforms are supported?
macOS 10.15+, Windows, and Linux — including first-class Wayland support with pure-Rust in-process text injection, plus X11.
Which models can I use?
Locally: Whisper GGML / GGUF (tiny → large), Parakeet TDT v3, Moonshine, Wav2Vec2 / CTC, and more. In the cloud: OpenAI, OpenRouter, Google Gemini, or any OpenAI-compatible endpoint. Download models in the built-in manager or import your own.
How do I install it, and what permissions are needed?
Download the installer for your OS from GitHub Releases. On first launch, download a local model or add a cloud key. On macOS, grant Microphone and Accessibility permissions — Accessibility is required for auto-paste.
What are the keyboard shortcuts?
Toggle recording with Ctrl / Cmd + Shift + Space from anywhere, and copy your last transcription with Ctrl / Cmd + Shift + C. Both are customizable in Settings.
Can I contribute?
Absolutely. Issues and pull requests are welcome on GitHub — bug reports, feature ideas, and patches all help.