Search Results for "active"

...Handy allows users to start transcription instantly using a configurable keyboard shortcut—press to record, release to transcribe—and automatically pastes the resulting text into any active text field. Its backend leverages OpenAI’s Whisper models for GPU-accelerated speech recognition and Parakeet V3 for efficient CPU-only transcription with automatic language detection. To further refine accuracy and responsiveness, Handy integrates Silero’s Voice Activity Detection (VAD) for silence filtering, ensuring only speech segments are processed.

...Optional AI enhancement can clean up, rewrite, format, or adapt dictated text for different tasks. Modes apply different models, prompts, context settings, and shortcuts according to the active app or website. A personal dictionary improves recognition of names, technical terms, and recurring phrases, while configurable global shortcuts support toggle and push-to-talk recording. Context-aware tools can use selected text, clipboard content, or visible screen text to improve the final output. The app is written in Swift, supports macOS 14.4 or later, can be installed through Homebrew, and is available under the GPLv3 license.

...Convert spoken words into text and translate them into multiple languages with professional-grade accuracy. Important Setup Requirements Before using this application, you MUST have: 1. Azure Account Setup Active Azure Subscription - Create a free account at portal.azure.com Azure Speech Service Resource - You must create your own Speech Service within your Azure subscription Valid API Key & Region - Obtain these credentials from your Azure Speech Service resource 2. Windows Privacy Settings CRITICAL: Microphone Access Required You must grant microphone access through Windows settings

NVIDIA Nemotron 3.5 Transcribe 30B-A4B is an open-weight speech and audio model designed for multilingual transcription, translation, speaker diarization, and audio understanding. It contains approximately 34B total parameters with 4.3B active, combining a hybrid Mamba-2–Transformer Mixture-of-Experts language backbone with dedicated speech recognition and speaker encoders. The model supports 40 languages, recordings up to one hour, and a 65,536-token context window. Its capabilities include verbatim and formatted transcription, speaker attribution, word-level timestamps, language identification, code-switching, and audio question answering. ...