SpeechFX VoiceGaming SDK is our award-winning software solution for video game voice command and control. SFX VoiceIn is the industry's most memory-efficient voice interface. Game developers worldwide can now build games that use a common API set across all game platforms.
The VoiceGaming SDK is optimized for game development where memory and processing power are at a premium.
• Nintendo WiiTM
• XBOX 360®
• PlayStation 3®
Current Languages (Additional Languages Upon Request):
• US English
• Canadian French
• European French
• Castillian Spanish
• Latin American Spanish
• Mandrin Chinese
The VoiceGaming SDK delivers superior voice recognition for video games, allowing developers to easily add voice-enabled command and control functions to increase the excitement and realism of game play. With this release, 'push-to-talk' is no longer required. The recognizer automatically detects speech without pushing a button first. See spec sheet for additional feature information.
The VG SDK includes the latest new feature- user adaptation capabilities. This function gives gamers the ability to adapt words to their own dialects, pronunciations, gaming environments, and other commands which are difficult to recognise. For example:
• A command that may sound similar to other commands.
• A command that may have different or alternate pronunciations as compared to a standard pronunciation.
• A game that may be marketed in a particular region where people speak a significantly different dialect from the
• Adverse background gaming conditions.
The VG SDK is optimized for minimal memory and CPU usage. It is available in multiple languages, as listed above.
The VoiceKaraoke SDK may be used to analyze a singing voice. It compares the phonetic timing and pitch of the voice to the reference song and reports the accuracy, which the game developer can display for the singer.
Pricing has changed to include a software license and per-unit royalty fee.
• Platforms: Win32, Microsoft 360/Xbox, Sony PS3, Ninteno Wii
• Languages: US/UK English, French, German, Italian, Spanish, Japanese, Korean. Languages
come with a dictionary and neural nets.
Lip Sync for Animated Characters:
The use of avatars and animated characters has grown significantly and the demand from users for better and better animations requires more natural lip and facial movements when the characters are speaking. Fonix VoiceSync generates the phonetic data and timing to create the 'human-like' lip and facial movements.
VoiceSync for Lip Sync Applications:
VoiceSync automatic speech recognition (ASR) is based on SpeechFX proprietary neural network technology and SFX VoiceIn. It provides accurate phonetic information about the speech that allows developers of animation products to more closely match lip, tongue, and facial animations to natural human movements. The Fonix VoiceSync software provides the phonemes and timing information and the corresponding markings for the audio stream. Fonix VoiceSync operates on scenarios where the text is provided as well as for applications, such as online voice chat, where only the audio is provided.
Fonix VoiceSync Features:
• Recognize phonemes in live or recorded speech
• Phonetic engine recognizes phonemes aligns them with their location in the speech audio.
• Two modes of operation:
- Utilize text of the utterance to provide the most accurate phonemes and their locations
- Generate phonetic estimates of free-form speech (e.g. online voice chat)
• Based on the Fonix VoiceIn 4.2 Speech Recognition Technology and SDK
• Languages: UK/US English, Canadian/European French, German, Italian, Japanese, Korean, Castilian/Latin
VoiceGaming Spec Sheet
VoiceGaming SDK Demo
VoiceSync Spec Sheet