Tag: ASR

Following Google’s release of new Speech API, we are happy to announce improved quality of call records transcription. No changes are required, your old code like

call.record({ transcribe: true, language: ASRLanguage.ENGLISH_US })

will be producing more accurate results. In addition to that, you can now specify output format

call.record({ transcribe: true, language: ASRLanguage.ENGLISH_US, format: “json” }) 

to get transcription in form of JSON file with timestamps for further processing. We are working on some examples that will be available in HowTo’s in the nearest future.

Hi everyone! We've been busy working on new cool features for you, many developers asked us about high quality speech recognition for both audio call records transcription and real-time recognition scenarios. We are happy to announce that this functionality is now available for all our developers.

We have finished the integration of TTS functionality with VoxEngine, now developers can specify text that will be converted into speech and sent to a call as an audio stream in 25 languages (for many of the languages you can choose between male and female voice). It will help developers build better cloud IVR, cloud contact center, cloud PBX, and other apps faster and automate a lot of standard interactions with a caller. To learn more about the function please check say function of the Call class and Language namespace in the VoxEngine Reference. In the near future we will add ASR (automatic speech recognition) function to let developers transcribe call records to text and do real-time speech recognition if required. Let us know if you have any questions and stay tuned!