VoxSigma is a suite of language-specific speech-to-text transcription software products offered byVocapia Researchfor Linux x86 and x86-64 platforms. VoxSigma is also available as a Web service.
Features
Platforms: Linux x86 and x86_64 (OpenSuse, Debian, Fedora, CentOS, Ubuntu, SuSE, Red Hat, ...)
API: command line tools, C++ library
Audio: studio (e.g. broadcast) and telephone bandwidths
Key functions: audio segmentation, speaker segmentation, language identification, spoken word transcription (speech-to-text)
Operating modes: batch, real-time, single or multi-threaded
Ouputs: XML with speaker diarization, language identification tags, word transcription, punctuation, confidence measures, numeral entities and other specific entities
Language Coverage
Arabic
(Arabic),
Dutch; Flemish
(Latin),
English
(Latin - United Kingdom),
English
(Latin - United States),
Czech
(Latin),
Finnish
(Latin),
French
(Latin),
German
(Latin),
Modern Greek (1453-)
(Greek),
Hebrew
(Hebrew),
Hindi
(Devanagari; Nagari),
Hungarian
(Latin),
Italian
(Latin),
Latvian
(Latin),
Lithuanian
(Latin),
Mandarin Chinese
,
Pushto; Pashto
(Arabic),
Persian
(Arabic),
Polish
(Latin),
Portuguese
(Latin),
Romanian; Moldavian; Moldovan
(Latin),
Russian
(Cyrillic),
Spanish; Castilian
(Latin),
Swedish
(Latin),
Turkish
(Latin)