NVIDIA released Nemotron 3.5 ASR, a new multilingual speech-to-text model benchmarked as the lowest-latency STT option tested, offering optimized performance for self-hosted voice agent infrastructure. The post covers deployment guidance and performance metrics across multiple languages, making it relevant for developers building real-time voice AI applications with Daily’s Pipecat framework.
Discovery
Learnings
- auto_storiesStories
- categoryAreas
- helpFAQ
- forumConversations
- descriptionPapers
- mailNewsletters
- video_libraryVideos
- timelineTimeline
Guidance
- codeTechnology of APIs
- business_centerBusiness of APIs
- campaignEvangelism of APIs
- gavelGovernance of APIs
- historyHistory of APIs
- account_balancePolitics of APIs
Toolbox
- domainProviders
- apiAPIs
- cloudSolutions
- buildTools
- verifiedStandards
- gavelRegulations
- horizontal_ruleHeaders
- layersOverlays
- extensionExtensions
- schemaSchema
- policyPolicies
- ruleRules