-
Multi-Structured Data Extraction with
StructuredDataMultiPlan: You can now extract multiple sets of structured data from calls by configuringassistant.analysisPlan.structuredDataMultiPlan. This allows you to define various extraction plans, each producing structured outputs accessible viacall.analysis.structuredDataMulti. -
Customizable Voice Speed and Language Settings: You can now adjust the speech speed and language for your assistant’s voice by using the new
speedandlanguageproperties inAssistant.voice. This enables you to fine-tune the voice output to better match your user’s preferences and localize the experience. -
Integration of OpenAI Transcriber: The
transcriberproperty in assistants now supportsOpenAITranscriber, allowing you to utilize OpenAI’s transcription services. A correspondingCall.endedReasonvalue,pipeline-error-openai-transcriber-failed, has been added to help you identify when a call ends due to an OpenAI transcriber error.
Get the (almost) daily changelog