Spoke
Spoke is a native macOS dictation application that provides instant voice-to-text transcription directly into any text field. It runs a high-performance local speech recognition model via CoreML, ensuring that audio never leaves the device for maximum privacy. Users can hold a customizable keyboard shortcut to speak and see their words appear instantly at the cursor. The app also features 'AI Skills,' allowing users to process transcriptions on the fly for tasks like translation, grammar correction, or summarization using their own API keys from providers like OpenAI, Anthropic, or local models via Ollama.
Privacy-focused macOS app for instant on-device dictation and AI-powered text processing.
- Dictating coding instructions directly into IDEs
- Real-time translation of spoken words into other languages
- Hands-free writing and emailing with automated grammar correction
- Quickly searching through a history of past voice-to-text entries
- After downloading the app on macOS 14+
- press and hold a designated push-to-talk key (like the Globe/fn or Right Command key). Speak naturally while holding the key; the on-device AI transcribes in real-time. Release the key to instantly insert the text into your active application. You can optionally configure AI Skills with your own API keys to transform your speech automatically.

Platform for on-device speech AI, enabling speech recognition and wake word detection.


AI chatbots for streamers to enhance audience engagement with real-time interactions.


AI-powered TOEFL Speaking prep with SpeechRater™ for accurate feedback and score prediction.


AI voice-based expense tracker for easy financial management.


Pay-as-you-go audio/video transcription service with AI content generation features.


AI tool to analyze accent and improve pronunciation accuracy.


Multilingual Speech-to-Text API with high accuracy in 14 languages.


AI-powered app to improve English pronunciation and speaking skills with personalized feedback.

Translates speech to text using the HTML5 Web Speech Recognition API.


A general-purpose speech recognition model by OpenAI.


AI-powered speech checker for English pronunciation, grammar, and fluency improvement.


AI platform for capturing, transcribing, translating, and analyzing language data.

Enhances ChatGPT with voice control, read-aloud features, and multi-language support.


AI copilot for interview prep & professional meetings with real-time assistance.


AI-powered tool to automatically remove profanity from videos.


AI-powered Quran app for recitation, memorization, and mistake detection.


Unifies speech recognition across 1,600+ languages using AI and LLM-enhanced decoders.


Kardome offers voice user interface technology for clear voice command input in any environment.




