Nvidia's free voice AI hears 40 languages — and names all 8 speakers

Nvidia released Nemotron 3.5 Transcribe on October 28, a free, open-weight model that transcribes audio in up to 40 languages, translates 31 languages to and from English, and tells up to eight speakers apart in a single recording.

The 30-billion-parameter model handles recordings up to an hour long and runs on a single chip, from a Jetson robotics controller or DGX Spark laptop chip up to Blackwell datacenter hardware. It works with recorded audio, not livestreams.

The release lands in a crowded voice-AI month, alongside Mistral's Voxtral 3, ElevenLabs' Realtime and Salesforce's Launa-Omni, and targets meeting and medical transcription — two of AI's most established workplace footholds.