PRODUCTS

Audioma®

The speech recognition technology that transforms speech into audio-synchronised text

Audioma® is the advanced speech understanding system that makes the content of any voice sequence available, both in real time and deferred.

Thanks to the MS Word add-on developed by PerVoice, Audioma® allows to refine and customize the transcription automatically obtained. The final output is a pdf file containing the text synchronized to the spoken word, freely distributable and accessible without the need for proprietary plug-in.

Audioma® can be installed on a stand-alone server or customer’s grid and has APIs for integration with third-party software.

Audioma® can be used both for specialized / technical vocabularies (e.g. medical and legal sectors) and for generalist domains (e.g. Broadcasting and Contact Center).

Maximum accuracy and quality of transcription

Automation, efficiency and time savings

Customization of linguistic models

Verbamatic®

Digital Archive

The indexing and search platform for audio / video content

Verbamatic® Digital Archive is the automatic indexing platform for audio/video media developed by PerVoice, which after transcribing the speech into text promote the search for the contents of interest.

Verbamatic® Digital Archive highlights the occurrences of the searched terms, retrieves the specific portion of the dialogue of interest, maintains the synchrony between transcribed text and audio.

Verbamatic® Digital Archive enables the extraction of data from open sources of the web and radio and television channels, providing valid support for the platforms for analyzing market trends, brand reputation and alerting on specific topics.

Verbamatic® Digital Archive is used for the retrieval of speech content within the multimedia repositories of companies, for the research of the topics of interest that emerged during the meeting, for the monitoring of radio and television broadcasters, and the creation of historical digital archives.

Instant access to search results

APIs for transcription extraction and media-metadata

User-friendly web interface

FlyScribe® Cloud

The “all-in-one” portal for voice transcription, subtitling and translation of audio/video

FlyScribe® Cloud is the web portal developed by PerVoice for automatic voice transcription of audio/video files, which allows the creation of permanently synchronized text files with the original audio.

In addition to speech-to-text transcription, FlyScribe® Cloud manage the automatic subtitling, translation and text-to-speech features for the creation of Audio Guide.

FlyScribe® Cloud integrate the revision tools developed by PerVoice, both to refine the transcribed texts and to refine the subtitle outputs, to complete the production workflow.

FlyScribe® Cloud is used in self-service mode on the web, integrated on the customer’s systems, or via APIs.

All-in-one: transcription, subtitling, translation and text-to-speech

Integrated editing and revision workflow

Wide availability of output formats (ask for the formats of your interest)

PerVoice Subtitling Workstation

The system for live subtitling of any event

PerVoice Subtitling Workstation (PSW) is the solution developed by PerVoice that allows the creation of accurate subtitles in real time.

An innovative interface speeds up the correction of automatic transcription, allowing the live editing of the subtitles a few seconds before their publication.

PSW connects to the most common subtitling systems, allowing event organizers, or television broadcasters, to control the entire subtitling process.

PSW is an appreciated support for people with hearing impairments, promoting a model of social inclusion and equal opportunities.

Accuracy and publication time of the subtitles at the highest levels

Availability of texts in synchronized document output

Model of social inclusion and equal opportunities