ModelsMulti-source
Nvidia 发布开源语音转写模型，支持 40 种语言
Voice AI in vogue: Nvidia releases new open transcription model
Why we picked it
Nvidia 白送了一个能转 40 种语言的开源转写模型，做会议记录、医疗转写可以直接用，不过要实时的话还得看 ElevenLabs。
Nvidia 发布了一款免费的语音转文字开源模型，支持最多 40 种语言的转写。该模型仅能处理录音文件，不支持实时音频流。这让它在会议记录和医疗转写场景有直接应用价值。实时语音场景则仍由 ElevenLabs 等对手的方案覆盖。
Original · techcrunch
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, 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.
