Loading...
Speek is a macOS voice assistant that lives in the Mac’s notch, turning speech into dictated or edited text, answers, and actions across supported apps and tools. It is aimed at Mac users who want hands-free writing, conversational help, and voice-controlled workflows.
Szept is a macOS app that combines keyboard dictation, AI text cleanup, screenshots, and screen recording for workflows involving AI agents and other Mac applications. It is intended for users who want to speak or show something on screen and paste the result into the app they are using.
Hemory is an always-on listening and memory tool that turns conversations, meetings and voice notes into searchable source material. Individuals can use its built-in Q&A or connect MCP-compatible agents to generate follow-ups, reports, journal entries and product documents.
Blurt is a free, open-source Mac dictation app that uses AssemblyAI's Dictation API to place finished spoken text into the field where you are typing. It is intended for people who want to replace some keyboard input with a hold-to-talk voice workflow.
MosMos is a voice-to-text productivity tool for macOS 15+ that turns speech into text in active fields, adapting wording to contexts such as chats, email, documents, code, and terminal workflows. It also records meetings and produces speaker-labeled transcripts, key takeaways, and to-do items.
QuietHint is a macOS meeting assistant that transcribes microphone and call audio on the Mac, labels speakers as You and Them, and suggests concise replies when questions arise. It helps people stay oriented during sales calls, support conversations, interviews, and other remote discussions without adding a bot to the meeting.
Flalingo AI Speaking Coach is a mobile language-learning app that assesses speaking level, provides live conversations with six AI coaching characters, and turns conversation feedback into personalized exercises. It supports practice in 12 languages for everyday, travel, and professional speaking situations.
SCAPTION provides real-time captions and AI translation for conferences, ceremonies, corporate events, and hybrid productions. Attendees access captions and participation tools on their phones by QR code, while organisers can send caption graphics to NDI, HDMI, or browser-based screens.
Jarvey is a Google Meet meeting assistant that answers questions aloud, recalls decisions from earlier calls, and creates missing task-board cards with owners and deadlines. It helps teams keep meeting context and follow-up work in one workflow.
Loqua is a voice-first desktop app for macOS and Windows that turns natural speech into polished, structured text across most apps. It also supports translation, voice editing, screen-based questions, and selected hands-free desktop actions.
Trancy Air is a shortcut-driven translation and writing assistant for macOS and Windows. It helps people translate selected or on-screen text, draft and replace text in other languages, dictate content, and practice pronunciation across desktop applications.
LazyReel is a macOS app for AI-assisted video editing and screen recording. It turns raw footage into edited clips with captions, cuts, B-roll, and music, and can work locally or with optional cloud AI.
Sayscroll is a browser-based AI teleprompter that follows your voice, records video in the browser, and supports 60+ languages. It is designed for creators, presenters, educators, podcasters, and content teams that want to read naturally and reduce retakes.
Ulpaso is a free, open-source Mac app that transcribes meetings on-device and saves the result as local Markdown files. It keeps notes, transcripts, settings, and search data on your Mac with no account or subscription required.
Gemini 3.5 Transcribe is Google’s speech-to-text model for real-time and recorded audio transcription. It helps developers and product users turn spoken language into clean, formatted text with support for multilingual audio, timestamps, and speaker attribution.
Speko is a voice AI router that benchmarks speech models by language and routes STT, LLM, and TTS through one API. It also offers a packaged infrastructure option and an enterprise contract path.
Tellie is a macOS teleprompter that follows the words you actually say, helping you stay on camera while using private notes. It is aimed at calls, interviews, presentations, and other speaking workflows where eye contact matters.
Comu Action Pro is a dedicated AI voice recorder that captures conversations and turns them into summaries, docs, slides, emails, and action items. It is aimed at people who want a physical device for recording and follow-up work rather than a phone-based note-taking app.
SubtitleGenerator is a browser-based AI subtitle tool for generating, reviewing, styling, and exporting subtitles from local video files. It helps creators and editors clean up transcripts, apply caption styles, and export subtitle files or burned-in video without leaving the browser.
Dehurdle is an AI voice simulation platform for practicing workplace conversations, from sales calls to leadership and support scenarios. It also offers a free speech diagnostic with instant feedback on pacing, filler words, and confidence.