Gemini 3.5 Live Translate is Google’s audio model for near real-time speech-to-speech translation in 70+ languages for calls, meetings, lessons, and broadcasts.
speech-core is a C++17 on-device voice-agent pipeline engine for VAD, streaming and batch speech-to-text, diarization, and text-to-speech.
Krisp Voice Translation API is a real-time speech-to-speech translation API for live calls and voice apps, with 61 languages, any-to-any pairing, noise cancellation, and custom vocabulary.
Vox is an on-device AI dictation app for Mac and Windows that turns speech into clean text on your clipboard. No account, offline-capable.
Wave is a native macOS dictation app that turns speech into text at the cursor, with local Whisper for offline privacy or Groq for faster transcription.
LocalClicky is a macOS voice assistant that runs locally to transcribe speech, interpret commands, inspect the screen, and control your Mac offline.
Clarafy is a browser writing assistant that polishes text in place with rewrites, tone adjustments, and voice dictation.
Shadow is a Mac app that captures what you see, hear, and say, then runs custom Skills on that context for notes, replies, and summaries.
AutoSubtitles is a browser-based AI subtitle generator and caption editor for video. Add, style, and export subtitles with no software or account needed.
Trace is a macOS meeting transcription app that records microphone and system audio locally, then delivers markdown transcripts with timestamped key moments.
Ringg Parrot STT V1 is a low-latency speech-to-text API for real-time and file-based transcription of Hindi, English, and code-mixed speech.
TongueType is a macOS voice dictation app that transcribes speech locally with Whisper AI and inserts text at your cursor. No cloud, accounts, or subscriptions.
Carbon Voice is an asynchronous voice messaging app for teams with people and AI agents, plus transcribed updates, voice or text replies, and desktop, mobile, watch, and widget access.
SpeakMac is an offline speech-to-text dictation app for Mac, converting live voice to text in your active window using on-device processing. 25+ languages.
SpeakON turns iPhone voice into polished text in the app you’re writing in—press one button, speak naturally, and keep working fast.
Harker is a free voice-to-text app for macOS. Dictate anywhere using a global shortcut—upgrade to Premium for AI writing styles, formatting, grammar fixes, and translation.
Grok Speech to Text and Text to Speech APIs by xAI convert audio and text with low-latency REST/WebSocket endpoints, multilingual support, diarization.
Ghost Pepper is a macOS app for voice dictation and meeting transcription, running 100% locally on Apple Silicon and converting speech to text.
Voice and screenshot input for AI builders on Mac. On-device transcription with no cloud upload and no account. One-time $49 download.
Walkie is a desktop speech-to-text app that inserts dictated text into any app with a hotkey. Choose Fast or Local mode.