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.
Voice AI in vogue: Nvidia releases new open transcription model
TE TechCrunch 
Key takeaways
Nvidia released Nemotron 3.5 Transcribe, a free open model for audio transcription in 40 languages.
- Nemotron 3.5 supports 31 languages and can handle hour-long recordings.
- It targets business and medical transcription with customizable industry jargon recognition.
- The model runs on various chips and joins Nvidia's open-weight voice models.
Summarised automatically by AI from the original article by TechCrunch. AI can make mistakes, so check the original for details.
Read the full story on TechCrunch You've read the opening, about 43 of 222 words. The full piece is published by TechCrunch.
Continue reading ↗ Story details
- Published
- By
- Julie Bort
- Section
- AI
- Length
- 222 words · about 1 min read
- Format
- Article
- Original
- techcrunch.com ↗
Related reporting
2 stories on this topic from 2 sources, oldest first.
- TechCrunch Voice AI in vogue: Nvidia releases new open transcription model (this story)
