OmniVoice
JSON →A unified speech model from k2-fsa for voice activity detection, speaker diarization, and speech recognition.
Capabilities
streaming
Dates
releasedMay 2024
Resources
API
full doc /v1/models/k2-fsa/OmniVoice
A unified speech model from k2-fsa for voice activity detection, speaker diarization, and speech recognition.