Voice AI in vogue: Nvidia releases new open transcription model
中文摘要
Nvidia发布免费语音转文字模型,支持40种语言录音转写,适用于会议和医疗,但不支持实时音频,实时功能由ElevenLabs等主导。
English Summary
Nvidia released a free speech-to-text model supporting 40 languages for recordings. It suits meeting and medical transcription but lacks real-time capabilities like ElevenLabs.
原文节选
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.