Nvidia Launches Free Open-Weight Transcription Model

Nvidia released Nemotron 3.5 Transcribe, a free open-weight model supporting transcription in up to 40 languages and translation between 31 languages and English. It handles recordings up to an hour long, distinguishes up to eight speakers, and claims to outperform rivals on benchmarks including Hugging Face's Open ASR Leaderboard. At 30 billion parameters, it runs on a single chip across devices from robotics controllers to datacenter chips. The model targets developers building business meeting and medical transcription apps. It works only with recorded audio, not livestreams. The release coincides with recent voice AI launches from Mistral, ElevenLabs, and Salesforce.