Why Audioma™ Box?

Accuracy - Flexibility - Choice
Audioma™ Box is the ideal Speech-To-Text solution for specialized or technical vocabulary typically used in fields like broadcasting, media monitoring, call centers, health care and reporting.

Contact us to get full control of your speech recognition solutions.

Great speech-to-text results

• Accurately recognize up to 95% of spoken words*.
  *In optimal conditions.

Freedom to choose

• Choose the languages you want from the many existing ones.
• Work with us to create new language models.
• The PerVoice Speech-To-­Text engine uses multicore parallel processing to make the recognition process fast and efficient.
• Speaker independence means there is no need to train the system.
• Add new words on-the-fly.

Get a bigger return from your audio data

• Analyze what customers say about you. (Speech Analytics)
• Find who is talking about you on TV. (Broadcast Monitoring)
• Make Audio/Visual archives easy to consult. (Media Indexing)

Speed up your transcription process.

• Get automatic drafts of speech. (Reporting)
• Create subtitles and closed captions efficiently. (Subtitling)

The future of ASR

Developed by researchers at Fondazione Bruno Kessler (FBK), the PerVoice Speech-To-Text engine has a proven record as “best of class”. PerVoice and FBK continue to add features and improve the engine to support your speech recognition solutions.