Cobalt VoiceBio

What Cobalt VoiceBio is

Cobalt VoiceBio provides voice biometrics for speaker verification and identification, including operation independent of spoken text. It converts speech into voiceprints that represent a speaker’s voice rather than the words spoken. StreamingVerify compares live audio with one voiceprint and returns a similarity score and match decision; StreamingIdentify compares live audio with a list and returns the best match or none. StreamingEnroll creates voiceprints and indicates how much more audio is needed to finish enrollment. Voiceprints can also be compared without resending audio or vectorized for indexing and downstream tasks. The engine runs on customer hardware, keeping audio and voiceprints inside the customer’s infrastructure. Cobalt lists embedded, on-premise, and private cloud deployment options. The product provides a gRPC API and pre-generated Go and Python SDKs, with instructions for generating SDKs in other languages. The trial supports 8 kHz and 16 kHz speech and lasts 100 days at no cost; Arm64 is not included. Listed system requirements are an x86_64 CPU, 500 MB disk space, and 2 GB RAM.