Open-source, local-first voice app for Windows, macOS and Linux that types dictation into any app, answers aloud, runs voice commands and records meetings.
sunerpy/voltip
Push-to-talk voice typing for desktop and Android: hold a hotkey, speak, and the text is pasted at your cursor.
Open-source alternative to:Dragon NaturallySpeaking
Wispr Flow
- Stars
- 89
- Forks
- 8
- Open issues
- 8
- Last commit
- 18 hours ago
What is it?
Voltip is a dictation app for Windows, Linux, macOS and Android. On the computer it records while you hold a hotkey, recognises speech in the cloud or on the local machine, optionally cleans the text up with an LLM, and pastes the result into whatever app has focus.
Recognition can use cloud providers such as OpenAI, Groq and Alibaba Cloud Model Studio, or on-device models such as Qwen3-ASR, SenseVoice and Paraformer, with GPU acceleration on supported hardware. A personal dictionary, replacement rules, per-app scenes and voice editing of selected text let users tune the output. Long recordings of up to two hours can be exported as SRT subtitles or plain text.
An Android app can work on its own, or pair end-to-end encrypted with the computer to act as its microphone and keyboard. The project is written in Rust with Tauri and React.
Key features
- 01Push-to-talk on a global hotkey or a single key, with a floating overlay showing the live transcript.
- 02Cloud recognition from several providers or on-device models, with GPU support on some platforms.
- 03Optional LLM clean-up, a personal dictionary and replacement rules.
- 04Voice edit: select text and speak an instruction to rewrite it.
- 05Long recordings with segmented transcription and SRT or text export.
- 06Android phone can act as the computer's microphone and keyboard over an end-to-end encrypted link.
Use cases
- Dictating emails, chat messages or documents into any desktop application.
- Transcribing long meetings or recordings and exporting subtitles.
- Using a phone as a wireless microphone and keyboard for the computer.
- Keeping speech recognition fully on-device for privacy-sensitive work.
Quick start
- 1
Install with the Windows PowerShell one-line script from the README
- 2
Or download the package for your platform from the releases page and install it
- 3
Start Voltip, then hold Ctrl+Alt+Space in any text field, speak, and let go
Things to know
- The one-line installers pipe a remote script into a shell, so review it before running.
- Windows builds are not code-signed yet, so SmartScreen warns on first start.
- Mac builds are not notarized, so macOS blocks the first start and needs manual approval.
- Wayland sessions have no global hotkey and need a compositor shortcut instead.
In collections
Topics
FAQ
- What is voltip?
- Push-to-talk voice typing for desktop and Android: hold a hotkey, speak, and the text is pasted at your cursor. Voltip is a dictation app for Windows, Linux, macOS and Android. On the computer it records while you hold a hotkey, recognises speech in the cloud or on the local machine, optionally cleans the text up with an LLM, and pastes the result into whatever app has focus.
- Is voltip free to use? What license does it have?
- voltip is open source under the AGPL-3.0 license. Check the license terms before using it in commercial products.
- Is voltip still maintained?
- Actively maintained. The last commit to voltip was on Nov 6, 2026.
- What can I use voltip for?
- Dictating emails, chat messages or documents into any desktop application. Transcribing long meetings or recordings and exporting subtitles. Using a phone as a wireless microphone and keyboard for the computer. Keeping speech recognition fully on-device for privacy-sensitive work.
- How do I install voltip?
- Install with the Windows PowerShell one-line script from the README Or download the package for your platform from the releases page and install it Start Voltip, then hold Ctrl+Alt+Space in any text field, speak, and let go
- Where can I get voltip?
- The source code and installation instructions are on GitHub: https://github.com/sunerpy/voltip
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source, local-first AI dictation app that turns speech into text on macOS and Windows, working offline with Whisper.
Offline-first voice-to-text dictation app for macOS and Windows that types transcribed speech at your cursor in any app.
Open-source macOS voice typing that transcribes speech and cleans it up locally on Apple silicon, then types into the active app.
A free, open source, offline speech-to-text desktop app that pastes transcribed words into any text field on Windows, macOS and Linux.
Open-source voice dictation app for Mac: hold Fn, speak, and cleaned-up text is typed wherever your cursor is.