The VoiceIn Standard Edition SDK enables developers to quickly and easily create speech interfaces for embedded processors, products and/or applications.
• Multiple platforms: Runs on numerous platforms and operating systems from small embedded to large server systems.
• Neural network technology: Provides accurate speaker-independent speech recognition, even in noisy environments.
• Efficient memory and CPU usage: Operates within memory and MIPs constraints or runs many concurrent channels on a server
system. See the product specification sheet for details.
• Multiple languages: Is available in U.S. and U.K. English, Canadian and European French, German, Japanese, Korean, Castilian
and Latin American Spanish, Swedish and Italian.
• Phonetic component: Aligns word phonetics with audio data, enabling animators to synchronize a character's facial
movements with the phonetic components of speech. Realistic facial movements are the result as animated characters "speak."
• Speaker independent: No training required to recognize speech.
• Accurate speech recognition: No training required to recognize speech in different and/or noisy environments. SpeechFX ASR
performs well with background speech and music.
• Natural speech: Accurately recognize continuous speech, enabling users to speak naturally without pauses in command-and-
• Improved return on investment (ROI): Is low-cost and easy-to-implement, enabling manufacturers to get their products to market
VoiceIn Spec Sheet
VoiceIn SDK Demo