Voice AI in vogue: Nvidia releases new open transcription model
Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings
Overview
Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings, not live audio, so it’s a big step for meeting and medical transcription tools while still leaving real-time use to rivals like ElevenLabs.
Ratings & Reviews
Rate Voice AI in vogue: Nvidia releases new open transcription model
Alternatives to Voice AI in vogue: Nvidia releases new open transcription model
View AllAutomatically generate captions and dubs for videos in multiple languages
Real-time transcription and audio processing for meetings and conversations.
Automatically generate captions and translations for videos.
Auto-generates captions and subtitles for videos in minutes.
All-in-one audio and video transcription solution
Local audio/video transcription via MCP for Claude and code editors.