Event ·Multi-source

Nvidia 发布开源语音转写模型，支持 40 种语言

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。

Current read

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。

11 sources56° AI heatLast updated 2026/10/28 15:00:00

Evidence

11 sources

Primary sourcetechcrunch

2026/10/28 15:00:00View source

Related source 1Artificial Analysis

2026/10/28 15:05:14View source

Related source 2vLLM

2026/10/28 15:26:59View source

Related source 3Decoder

2026/10/28 15:49:39View source

Related source 4rohanpaul_ai

2026/10/27 16:41:33View source

Related source 5Hugging Face: Blog

2026/10/28 14:58:17View source

Related source 6TestingCatalog

2026/10/28 09:58:40View source

Related source 7Gorden Sun

2026/10/28 16:01:32View source

Related source 8CoreWeave

2026/10/26 17:38:48View source

Related source 9面壁智能 ModelBest

2026/10/27 11:20:48View source

Related source 10Detik Inet

2026/10/28 11:08:03View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story