voice-mate

Voice assistant for Windows: press a hotkey, speak, and the transcription lands in your clipboard. Local Whisper with GPU acceleration. https://www.youtube.com/watch?v=T9H30G-AbZo

A new way for AI to search for data

View on GitHub

3GitHub stars

211commits on main

0forks

v0.2.0latest release, 2026-10-29

Python 96.8%, PowerShell 1.6%, Inno Setup 1.1%, Makefile 0.4% · created 2026-03-24 · last push 2026-10-29

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit fe4f86097d (2026-10-28). main is 21 commits ahead.

Selected work

Álli Terhorst
@alliterhorst

“switchable CPU and GPU speech-to-text modes with in-app in…”. 45 files, 2,026 lines in tests, app/companion, app/setup.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-29. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

clipboardcudafaster-whispergpu-acceleratedhotkeyproductivitypythonspeech-to-text

Example questions

How does voice-mate implement clipboard?
What does app/companion do in voice-mate?
Show the cuda code in voice-mate.

Inside the indexed corpus

Languages by size: Python 96.8%, PowerShell 1.6%, Inno Setup 1.1%, Makefile 0.4%, AutoHotkey 0%.
On GitHub since 2026-03-24, last push 2026-10-29, 211 commits on main.
The pin is 21 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported MIT for nano-br/voice-mate on 2026-10-29, and the LICENSE file at commit fe4f86097d was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Álli Terhorst (@alliterhorst) has 1 selected repository on the hub.

Using XERJ with voice-mate

Search an OpenAPI spec so an agent can find endpoints The hub files it under API design and specification.
ripgrep vs a code index for coding agents: 30 tasks
Best MCP servers for local code search in 2026, compared
Best grep alternative for AI coding agents (2026)

The prompt

Paste it into your AI agent. It clones nano-br/voice-mate at the pinned commit and indexes it on your machine.

Search the GitHub repository nano-br/voice-mate with XERJ (https://hub.xerj.org/corpus/nano-br--voice-mate).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/nano-br/voice-mate voice-mate && git -C voice-mate checkout fe4f86097d9c2f59813b00bfc6a9a711b0c9ff14
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./voice-mate --url http://127.0.0.1:9200 --prefix voice-mate --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Álli Terhorst API design and specification corpora dunorth595--ai-agent-chat agentscope loldrivers TypeWhisper/typewhisper-mac gabry-ts/kaiku prompt-agency/react-native-voice-activator

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.