Mistral releases Voxtral Transcribe 2, a new family of audio-to-text models, including an open-weights real-time transcription model.
Mistral releases Voxtral Transcribe 2, a new family of audio-to-text models, including an open-weights real-time transcription model.
A developer documents building HyperVideo, an interactive AI-powered video player with real-time Q&A using Azure AI services and Blazor.
A developer details building an automated transcription bot using Claude AI and Apple's speech framework to improve podcast and video caption accuracy.
MacWhisper's new Automatic Speaker Recognition feature, powered by NVIDIA Parakeet, accurately identifies speakers in audio transcripts.
A technical guide on setting up and using whisper.cpp for local audio transcription, including building, patching, and practical usage.
Aiko is a privacy-focused app for high-quality, on-device audio transcription using OpenAI's Whisper model, available on Apple platforms.
A tutorial on using Deepgram's Node.js SDK for speech-to-text transcription, including building an Express app to transcribe audio from URLs.
A guide to using PowerShell to automate batch transcription of audio files with the Azure Speech Service REST API.
