Voxt:Mac 上的 AI 語音工作流

Voxt 是一款面向 macOS 的桌面語音輸入與轉錄工具,可將語音轉為文字,並利用語言模型去除口頭禪、修正標點、優化結構,支援本地模型離線處理、會議轉錄與分析、翻譯改寫以及按應用客製增強規則。

造訪官網

關於這個工具

Voxt

是什麼 Voxt 是一款面向 macOS 的桌面語音工作流應用,把音訊擷取、語音辨識、文字清理、翻譯、插入、歷史記錄以及可選的遠端呼叫整合進 Mac 的實際書寫介面。你只需把游標留在訊息、文件、瀏覽器輸入框或編輯器中,即可直接開始語音輸入。

主要能力

  • 桌面語音輸入:從任意聚焦的 Mac 輸入位置擷取語音並轉為文字。
  • AI 轉錄與增強:轉錄後可用語言模型去除口頭禪、修正標點、改善結構,並套用你的自訂指令。
  • 按應用客製規則:可為不同應用和網站建立不同的模型增強規則,例如讓回應保持 SQL 語法與格式。
  • 會議轉錄與分析:支援帶波形時間軸、音訊回放和更持久歷史記錄的可編輯會議轉錄;可匯入會議檔案進行分析,支援有界音訊視窗、完整轉錄、連續說話人分離、進度與取消。
  • 錄音分析:可分析 Mac 上已有的錄音,支援最長 12 小時的會議檔案限制,並採用排隊背景處理。
  • 多模式擷取:可透過 Meeting、Captions 或 Recording 模式擷取系統音訊、麥克風音訊或兩者。
  • 全域語音筆記:可全域喚醒語音筆記擷取,無需先開啟筆記應用。
  • 待辦標記:擷取的筆記可攜帶待辦狀態,便於在浮動筆記管理器中區分可執行事項與一般想法。

處理與隱私

Voxt 會說明本地處理涵蓋哪些部分,並為非模型推論的部分留出空間:下載、帳戶、計費、分析、支援與更新。帳戶功能、計費、下載、網站分析和遠端提供方需要網路連線。實際處理時間和資源佔用取決於檔案、所選模型、硬體以及是否啟用說話人分析。

平台與取得

Voxt 支援 macOS 與 Windows,採用 freemium 模式,專案為開源,可在 GitHub 上取得。

典型場景
  • ” It is compressing capture, cleanup, translation, and rewrite into the real writing surface of macOS
  • ” It tells you what local processing covers, and it leaves room for the parts of the product that are not model inference: downloads, accounts, billing, analytics, support, and updates
  • A captured note can carry a to-do status so you can distinguish actionable items from general ideas in the floating note manager
  • A desktop app starts from the current focus With Voxt, the usual flow is simpler: Leave the cursor in the message, document, browser field, or editor
  • A voice workflow can include audio capture, speech recognition, cleanup, translation, insertion, history, and optional remote calls
  • A voice workflow usually has several steps: capture audio, recognize speech, clean up the transcript, translate or rewrite it, save a result, and sometimes send something to another service
  • Account features, billing, downloads, website analytics, and remote providers need a connection too
  • Actual processing time and resource use depend on the file, selected model, hardware, and whether speaker analysis is enabled

功能與使用情境

” It is compressing capture, cleanup, translation, and rewrite into the real writing surface of macOS” It tells you what local processing covers, and it leaves room for the parts of the product that are not model inference: downloads, accounts, billing, analytics, support, and updatesA captured note can carry a to-do status so you can distinguish actionable items from general ideas in the floating note managerA desktop app starts from the current focus With Voxt, the usual flow is simpler: Leave the cursor in the message, document, browser field, or editorA voice workflow can include audio capture, speech recognition, cleanup, translation, insertion, history, and optional remote callsA voice workflow usually has several steps: capture audio, recognize speech, clean up the transcript, translate or rewrite it, save a result, and sometimes send something to another serviceAccount features, billing, downloads, website analytics, and remote providers need a connection tooActual processing time and resource use depend on the file, selected model, hardware, and whether speaker analysis is enabledAdded editable meeting transcripts with waveform timelines, audio playback, and more durable meeting history.Added imported meeting file analysis with bounded audio windows, full transcription, continuous speaker diarization, progress and cancellation, and history audio preference handling.After the meeting, use the result for summary and analysis, then ask follow-up questions about decisions, action items, unresolved topics, or other details in the recorded conversationafterward, review speakers and timestamps, generate a summary, analyze the conversation, and ask follow-up questions

使用分析

變現方式
  • 免費增值
成熟度信號
  • 開源
上手難度
  • 中

資訊來源

每筆檔案都保留來源與最近驗證時間。

相似工具

Amazon Web Services, Inc.
aws.amazon.com
76

Amazon Web Services offers reliable, scalable, and inexpensive cloud computing services. Free to join, pay only for what you use.

開啟詳情
Skills Manager
skillsmanager.freeourdays.com
74

Skills Manager 是一款免費開源的桌面工具,用於在 32 款 AI 程式設計工具之間管理、同步、安裝、翻譯和掃描 Agent Skills。它透過符號連結讓編輯即時同步到各工具,無需手動複製。

開啟詳情
RESTai
restai.cloud
69

RESTai 是一個開源、自託管的 AIaaS(AI 即服務)平台,透過統一的 REST API 和完整的 Web UI 提供 RAG、智慧代理、MCP 工具、視覺化邏輯和應用程式建構器。採用 Apache 2.0 授權。

開啟詳情
S
Synkora
synkora.ai
84

Synkora 是一個開源、可自託管的 LLM 應用平台,用於建置和部署可自訂的 AI 智慧代理,涵蓋產品管理、工程、客戶支援和行銷等場景。

免費

開啟詳情