Soniox already offers a very accurate speech recognition transcription engine for English language, and the company now released an audio AI solution that automatically annotates the transcribed audio with real-world entities and their contextual information, providing an augmented representation of the audio stream in real-time and low-latency. Soniox offers this novel technology in Soniox APIs, iOS app and web application. Soniox already offers a very accurate speech recognition transcription engine for English language, and the company now released an audio AI solution that automatically annotates the transcribed audio with real-world entities and their contextual information, providing an augmented representation of the audio stream in real-time and low-latency. Soniox offers this novel technology in Soniox APIs, iOS app and web application. As anyone who as tried transcription engines based on speech recognition, approximately 10% of the resulting accuracy depends on context, which is where all automatic systems fail most spectacularly (automatic closed captions provide the most hilarious and exasperating examples).