https://victorsalles.com/en/tags/tts/Recent content in Tts on Victor SallesHugoen-usSun, 22 Mar 2026 00:00:00 +0000https://victorsalles.com/en/posts/building-offline-voice-system-macos/Sun, 22 Mar 2026 00:00:00 +0000https://victorsalles.com/en/posts/building-offline-voice-system-macos/How I built a fully offline text-to-speech and speech-to-text system for macOS using Kokoro-82M and mlx-whisper — no cloud APIs, streaming audio in under a second.https://victorsalles.com/en/projects/voice-automation/Sun, 01 Mar 2026 00:00:00 +0000https://victorsalles.com/en/projects/voice-automation/<h2 id="offline-voice-io-for-macos">Offline voice I/O for macOS</h2> <p>A complete text-to-speech and speech-to-text system for macOS that runs entirely on-device. No cloud APIs, no subscriptions — just local AI models doing real work.</p> <p><strong>The problem:</strong> I spend hours reading and writing text on screen. I wanted a way to have my Mac read anything to me with a single hotkey, and transcribe audio without sending data to external servers.</p> <p><strong>What it does:</strong></p> <p>Press <code>⌥S</code> and whatever text you&rsquo;ve selected (or copied) gets read aloud using Kokoro-82M, an 82-million parameter TTS model running locally on Apple Silicon. The system automatically detects whether the text is Portuguese or English and picks the right voice. Audio starts streaming in under a second — no temp files, no waiting for the full synthesis to finish.</p>