Released: May 23, 2023
Updates in 2023 (10.0.1.0)
Fehlerkorrekturen
- Developer Workbench 2023 64-bit menu shortcut launches 2022 64-bit edition.
- Speech Recognition Grammars with Semantic Interpretation Markup fail to load (enable).
- Developer Workbench 2023 registration generates invalid credentials.
- Cross-platform TChantRecognizer and TChantSynthesizer classes build fails when targeting Android and iOS.
- Cross-platform TChantRecognizer and TChantSynthesizer unable to be downcast.
- Cross-platform sample build fails in RAD Studio 11.3 with...
Released: Mar 27, 2023
Updates in 2023 (10.0.0.0)
Funktionen
- Updated support for Acapela, Cepstral, CereProc, Dragon NaturallySpeaking, Microsoft Windows Media (WinRT and UWP), Microsoft SAPI5, System.Speech, Microsoft.Speech and Microsoft Speech Platform speech technologies.
- Updated Microsoft .NET assemblies for .NET Frameworks 4.5+, 3.1, 5.0, 6.0 and 7.0.
- Updated Java JAR libraries for JDKs 1.8, 11, 13, 14, 15, 16, 17, 18 and 19.
- Updated Microsoft Visual Studio, Embarcadero RAD Studio, JDK (Eclipse, NetBeans, et. al.), Android Studio, and...
Released: Nov 11, 2022
Updates in 2022 (9.0.0.11)
Funktionen
- Microsoft .NET 7 assemblies are now available for GrammarKit, KinesicsKit, LexiconKit, ProfileKit, SpeechKit, VoiceMarkupKit and VoiceXMLKit.
Released: Oct 11, 2022
Updates in 2022 (9.0.0.8)
Funktionen
- New Java 19 jars are now available for AudioSearch, GrammarKit, KinesicsKit, LexiconKit, ProfileKit, SpeechKit, SpeechManager, Talk&Listen, VoiceMarkupKit, and VoiceXMLKit.
Released: Sep 6, 2022
Updates in 2022 (9.0.0.3)
Funktionen
Command and Dictation vocabulary support for mobile and Mac platforms
- With command-based recognition, all types of applications are now possible using speech recognition. This is because recognized speech can be matched and associated with properties that drive data capture, selection, and navigational tasks.
- Dictation-based or continuous recognition is also supported where utterance capture continues for long annotations until stopped by the app.
- Mobile and Mac apps now enjoy...
Released: Jul 7, 2022
Updates in 2022 (9.0.0.0)
Funktionen
- Updated support for Acapela, Apple, Cepstral, CereProc, Google, Microsoft and Nuance speech technologies.
- Updated Microsoft .NET assemblies for .NET Frameworks 4.5+, 3.1, 5.0 and 6.0.
- Updated Java JAR libraries for JDKs 1.8, 11, 13, 14, 15, 16, 17 and 18.
- Updated C++, Embarcadero C++Builder, and Embarcadero Delphi libraries.
- Updated Android Java JAR libraries.
- Updated Objective-C and Swift libraries for Apple iOS and Mac.
- Updated Developer Workbench UI for streamlined development and...
Released: Dec 14, 2021
Updates in 2021 (8.0.1.1)
Funktionen
- New Speech Manager enables applications to easily create and schedule speech processing requests.
- Developers now have the ability to quickly and easily generate and manage speech processings with a few lines of code. Speech Manager provides high-value capabilities that leverage Acapela, CereProc, Cepstral, Microsoft, and Nuance speech technologies.
- There are two types of speech requests supported: transcription and speech synthesis.
- With transcription requests, audio streams (i.e...
Released: Oct 18, 2021
Updates in 2021 (8.0.1.0)
Funktionen
- Improved speech recognition accuracy and speech synthesis clarity with phonemes.
Released: Jul 8, 2021
Updates in 2021 (8.0.0.0)
Funktionen
Gain development productivity and runtime efficiency
- Learn by Example - See how easy it is to develop software that speaks, listens and detects movement with example apps. Simply compile and run sample apps using your favorite IDE and programming language.
- Direct Speech Recognition Requests - You can now recognize speech directly bypassing vocabulary management and queue processing. StartRecognition method enables continuous speech recognition if no vocabularies are enabled and the...
Released: Mar 16, 2021
Updates in 2020 (7.0.3.2)
Funktionen
- Audio Search helper class library now includes support for word spotting searches. Audio is word spotted with a list of keywords (i.e., single words or phrases) first. Then one or more searches may be performed to match a keyword originally used in the word spotting. Matches are returned as offsets in seconds.
