Multilingual speech-to-text software that transcribes audio, identifies speakers and languages, and runs on-premise or as a web service.
Vocapia Research builds the VoxSigma suite, which covers audio segmentation, speaker diarization, language identification, transcription, keyword search and audio-text alignment. Output is structured XML with time-coded words, speaker labels, confidence scores and punctuation. Speech-to-text covers about 30 languages, including Arabic, English, French, German, Mandarin, Russian, Spanish and Urdu, and language identification covers 100 languages and dialects. It is sold as an on-site license, a REST API, a GUI service or batch processing. Customers include parliaments, broadcasters, call analytics teams and defense users, and the company takes part in national and international R&D projects.
Speech-to-Text
HQ COUNTRY
Île-de-France, France
FOUNDED
2000
Is this your company? To claim this listing or update its details, contact us at sunil@uniocommunity.com
