Intelligent Voice Processing & Indexing
As an NVIDIA partner, Intelligent Voice’s
proprietary algorithms further accelerate NVIDIA GPU processing, providing results in a fraction of the time of our competitors, and with no loss of accuracy.
Processing is robust across
near & far field audio, capture methodologies and recording quality.
Supports
over two dozen American, Asian and European languages for transcription, including multiple dialects and accents, with the ability to customize lexicons and models case by case, and
detect and transcribe language changes mid-conversation.
Unattributed biometric speaker separation can be optionally applied to the transcribed text. Alternatively, if the creation and use of physiological biometric data is not advisable or not permissible in a jurisdiction, biometric speaker separation can remain disabled across the Relativity instance.
Processed audio and video content fits the same Relativity workflows as all other data for review, analysis, redactions and productions: start with a Relativity Search Set, conclude with one or more Relativity Production Sets.
A separate voice identification capability is also available, including prior to Relativity, as detailed in the separate listing for
Intelligent Voice Identification.
Intelligent Voice Pricing
Intelligent Voice provides simple, predictable cost models, with both pay as you go and bulk pre-purchase pricing options.
Pricing is by duration of processed media, independent of channel and / or speaker count, media file sizes, and features used.
Documented intelligent culling processes reduce the volume of media to be processed, or even hosted, in the first place.
Free use for approved Relativity
Justice for Change projects, leveraging the unique capabilities of Intelligent Voice and Relativity to positively impact racial and social justice in our communities.
Reach out to us with any questions you may have, or to arrange a walk through or to discuss next steps.