Audio
buzz
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
★ 21.8k starsMIT
View guide →// audio · hehehai/voxt
voxt
voxt is an open-source audio project by hehehai (hehehai/voxt on GitHub). It has 853 GitHub stars and 65 forks, is released under the Custom license, and was last updated on GitHub on 4 October 2026.
A macOS voice assistant that turns speech into actions and notes.
💎 Hidden gem★ 853 stars⑂ 65 forksCustomupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- hehehai/voxt
- GitHub stars
- 853
- Forks
- 65
- License
- Custom
- Last updated on GitHub
- 4 October 2026
- Category
- Audio
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Install on macOS
Download and run the native Swift app.
- Speak your thoughts
Capture ideas, meetings, or instructions by voice.
- Get clean output
Speech becomes polished text and structured notes.
- Trigger actions
Let it automate repetitive tasks across apps.
// features
Why people love it
Voice productivity
Turns raw speech into clean text and useful actions.
macOS native
Swift app built for the Mac desktop experience.
Structured knowledge
Organizes dictated content into usable notes.
Meeting friendly
Helps capture and process spoken conversations.
Task automation
Automates repetitive workflows triggered by voice.
Custom license
Check the repo terms before commercial use.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/hehehai/voxt.git cd voxt - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Turn meeting speech into structured notes.
- Capture ideas hands-free on a Mac.
- Dictate emails that get auto-polished.
- Automate repetitive tasks with voice triggers.
Advertisement
// faq
Questions, answered
Who maintains voxt?
It is an open-source project at hehehai/voxt with 65 forks. Check the repo's contributors and recent commits to see how active maintenance is.
Is voxt free for commercial use?
It uses a custom license — read the repo's terms before using it commercially.
Which platforms are supported?
It is a Swift app built for macOS.
Does it just transcribe, or more?
More — it turns speech into clean text, actions, and structured knowledge.
How is it different from plain dictation?
It aims to be a productivity assistant: organizing and acting on speech, not just typing it.
// keep exploring
Similar tools
Audio
RealtimeSTT
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
★ 10.2k starsMIT
View guide →Audio
RealtimeTTS
Converts text to speech in realtime
★ 4.0k starsMIT
View guide →Audio
hifi-gan
GAN vocoder that turns mel-spectrograms into high-fidelity speech audio, fast enough for real-time use.
★ 2.4k starsMIT
View guide →Audio
gTTS
gTTS — Python library and CLI that turns text into spoken mp3 via Google Translate's speech API
★ 2.6k starsMIT
View guide →Audio
Kokoro-FastAPI
Turn the beloved Kokoro voice model into an OpenAI-compatible speech API with one Docker command.
★ 5.5k starsApache-2.0
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if voxt is not the right fit.
- MoneyPrinterTurbo★ 128.3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to voxt — keep exploring the shelf either side of it.
- whisper.api★ 914
A ready API for speech-to-text with per-user access control.
- TTS-Voice-Wizard★ 809
Speech-to-text-to-speech for VRChat, VTubers, and streamers.
- vonage-php-sdk-core★ 931
Official Vonage PHP SDK for SMS, voice, TTS, and 2FA APIs.
- NotelyVoice★ 803
100% private voice transcription for Android and iOS, on-device.
- Jarvis-Desktop-Voice-Assistant★ 969
A Python voice assistant that runs system commands by voice.
- vui★ 767
A tiny conversational TTS model with cloning, streaming, and CPU speed.
Get voxt
Free and open — grab the source, star the repo, and start creating.