Voxt icon
Voxt icon

Voxt

AI-powered local-first voice input app for Mac transforms speech into clean, structured text, performs real-time translation, customizable per-app automation, global shortcuts, voice notes with todo tracking, live meeting transcription, and detailed summaries for any workflow.

home

Cost / License

  • Free
  • Open Source

Platforms

  • Mac  os 15+
5likes
0articles

Features

Voxt News & Activities

Highlights All activities

Recent activities

  • Whisprtypr icon
    Shejan-Mahamud added Voxt as alternative to Whisprtypr
  • FU Flow icon
    Lu-Ram added Voxt as alternative to FU Flow
  • voconly icon
    xinkyle added Voxt as alternative to voconly
  • SayWrite  icon
    Jihad-Ahmed-7252 added Voxt as alternative to SayWrite
  • Vocatim icon
    POX added Voxt as alternative to Vocatim
  • Holos icon
    Yuramos added Voxt as alternative to Holos
  • Iris flow icon
    Akash-Vishwakarma added Voxt as alternative to Iris flow
  • HoldToType icon
    vitalii_yemets added Voxt as alternative to HoldToType
  • Commander Flow icon
    ptrs_ltd added Voxt as alternative to Commander Flow
  • Bulbul icon
    Romanch-Roshan-Singh added Voxt as alternative to Bulbul

Voxt information

AlternativeTo Categories

AI Tools & ServicesOffice & Productivity

GitHub repository

  •  824 Stars
  •  61 Forks
  •  1 Open Issues
  •   Updated  
View on GitHub
Voxt was added to AlternativeTo by Guan Wei on and this page was last updated .
No comments or reviews, maybe you want to be first?

Official Links

What is Voxt?

AI-Powered Voice Productivity App

An intelligent voice productivity assistant that turns speech into clean text, useful actions, and structured knowledge. It helps users capture ideas, communicate naturally, automate repetitive tasks, and stay productive across different apps and workflows.

Core Features

1. Transcription

Convert speech into text instantly. The transcription result can be enhanced by an AI model to:

  • Remove filler words and unnecessary repetition
  • Correct grammar and punctuation
  • Improve readability and structure
  • Format content according to user preferences
  • Apply customizable processing rules

The enhanced text is automatically inserted into the active input field.

2. Translation

Translate transcription results into a selected target language. Users can also select specific text and translate only the chosen content.

3. AI Voice Conversation

Select text or activate conversation mode directly to interact with an AI voice model. Conversation results can be:

  • Copied to the clipboard
  • Inserted directly into the active input field
  • Used as part of an ongoing voice interaction

4. Voice Notes

Capture ideas and reminders from anywhere with a global shortcut. Voice notes are automatically converted into text and can include todo status management.

A floating note panel allows users to:

  • Quickly review and manage notes
  • Mark notes as completed
  • Drag and drop notes into input fields
  • Insert notes into other applications instantly

5. App and Web Automation

Create customized AI enhancement rules for different applications and websites.

For example, in SQLEditor:

“Query all user data”

The app can automatically convert it into:

SELECT * FROM "user";

Users can also configure automated keyboard actions. After text is inserted, the app can trigger predefined keys—for example, automatically submitting the query.

6. Meetings and Live Captions

Meeting mode supports three recording options:

  • Meeting Mode: System audio and microphone
  • Caption Mode: System audio only
  • Recording Mode: Microphone only

The app transcribes conversations in real time and supports live translation. After the meeting, users can review detailed records including:

  • Speaker identification
  • Timestamps
  • Full transcripts
  • Translations
  • Meeting summaries
  • AI-powered analysis
  • Follow-up questions and answers

Designed for Flexible Workflows

The app combines speech recognition, AI enhancement, translation, note-taking, and automation in one unified experience. Whether users are writing, coding, attending meetings, capturing ideas, or working across multiple applications, they can speak naturally and let the app transform their words into structured, actionable content.