Loading...
Loqui is a Mac and Windows desktop voice-to-text tool that turns natural speech into formatted text at the cursor in apps where you can type. It supports multilingual dictation, context-specific output, and meeting transcription with structured notes.
sideOS is a macOS AI assistant that lives in the MacBook notch and turns spoken requests into screen-aware computer actions, dictation, background tasks, and meeting summaries. It is aimed at Mac users who want to control apps and coordinate work with voice commands.
Eleven Realtime is a speech-to-speech model family for building low-latency voice agents in ElevenAgents or through an OpenAI-compatible API. It offers v1 Mini for natural conversation and v1 Max for complex reasoning and multi-step tool use.
Kugel Ear 1 is a speech-to-text service for voice agents that flags uncertain words and returns candidate spellings with probabilities. It also detects when a caller’s turn ends, helping conversational applications clarify names, addresses, codes, and other error-sensitive inputs.
Eleven Realtime Translation converts live speech into natural translated audio for two-way conversations across more than 90 languages. It is intended for telecom, contact center, event, and other multilingual communication workflows, with selectable voices and streamed captions or transcripts.
Voxtral 3 combines multilingual speech transcription, expressive text-to-speech, and a real-time voice agent SDK for phone and web conversations. It helps teams build assistants and workflows that can understand spoken requests, use connected tools, and respond naturally.
SpeechFast is a local voice dictation app for Apple Silicon Macs that transcribes and cleans up speech on the device, then inserts the text at the cursor. It suits users who need offline dictation and want audio to stay off remote servers.
Openbroca is a native AI dictation app for Mac that turns natural speech into refined text in the focused field of the app you are using. It supports multilingual dictation, translation, personal vocabulary, and optional screen context for Mac users who draft by voice.
Nani? is a Mac app that displays live translated subtitles for meetings, with a focus on Japanese–English conversations and support for nine languages. It also provides nuance notes, question-directed alerts, catch-up, speaker-labeled transcripts, and meeting summaries for multilingual teams and calls.
Table Canon turns uploaded tabletop RPG session audio into recaps, outlines, and a persistent campaign desk for game masters. It supports between-session preparation with World and Story views, open-thread tracking, Prep suggestions, and cited Ask answers about earlier sessions.
OpenWhispr is open-source dictation and speech-to-text software for macOS, Windows, Linux, and iOS. It helps developers, writers, teams, and people seeking hands-free input dictate into existing apps, transcribe audio, and create meeting notes using local models or optional cloud processing.
Foley is a voice-first task management app that turns spoken or typed instructions into organized tasks with dates, projects, and other details. It helps individuals and collaborators capture work quickly, plan their day, and access the same list across desktop, web, mobile, and supported watches.
Voicera is a macOS app that turns natural speech into cleaned, punctuated writing at the cursor and provides AI actions for selected text. It is designed for people who want to draft, revise, translate, or ask questions across the apps they use on a Mac.
VocaScript is a browser-based AI transcription tool that converts uploaded audio, video, public media links, and browser-tab media into editable text. It supports 100+ languages, speaker detection, timestamps, translation, transcript editing, and TXT export, with additional capacity and formats on paid plans.
ParakeetAI is a real-time AI assistant for job interviews, sales calls, client meetings, and technical conversations. It transcribes live speech, detects questions, suggests answers, and supports mock interviews plus post-call transcript review.
SpeechShield is a Mac AI copilot for job interviews, client meetings, and live translation. It transcribes conversations and provides resume-, job-posting-, or meeting-material-based talking points in a desktop overlay or paired phone browser.
Jarq is a Mac productivity tool for translating, rewriting, shortening, and improving selected text directly in the app where you work. It also adds punctuated dictation at the cursor, including optional offline recognition on Apple Silicon Macs.
Angebotsmeister ist eine KI-gestützte Angebots- und Rechnungssoftware für Handwerksbetriebe. Aufträge und erledigte Arbeiten lassen sich per Sprache erfassen, in strukturierte Positionen umwandeln und als Angebot oder Rechnung weiterverarbeiten.
Yubi is a press-to-talk dictation and screen-assistance utility for Apple Silicon Macs running macOS 26. It transcribes speech locally into the app at the cursor and can help identify controls in the frontmost window, making it useful for hands-free writing and navigation across Mac apps.
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.