How it Works
ASAPP’s AutoTranscribe service is powered by a speech recognition model that transforms spoken form to written forms in real-time, along with punctuation and capitalization. To optimize performance, the model can be customized to support domain-specific needs by training on historical call audio and adding custom vocabulary to further boost recognition accuracy AutoTranscribe was also designed to be fast enough to show an agent what was said immediately after every utterance. AutoTranscribe can be implemented in three main integration patterns:- WebSocket API: All audio streaming, call signaling, and returned transcripts use a WebSocket API, preceded by an authentication mechanism using a REST API.
- IPREC Media Gateway: Audio streaming sent to ASAPP media gateway and call signaling sent via a dedicated API; transcripts are returned either in real-time or post call.
- Third Party CCaaS: Audio is sent to ASAPP media gateway by a third party contact center as a service (CCaaS) vendor and call signaling sent via API; transcripts are returned either in real-time or post call.
AutoTranscribe Product Guide
Learn more about AutoTranscribe in the Product Guide
Get Started
To get started with AutoTranscribe, you need to:- Follow the Developer Quickstart to get your API Credentials
- Choose the integration that best fits your use case:
Platform Connectors
Media Gateway: SIPRec
Transcribe audio from your SIPRec system using the ASAPP Media Gateway
Media Gateway: Twilio
Transcribe audio from your Twilio system using the ASAPP Media Gateway
Media Gateway: Amazon Connect
Transcribe audio from your Amazon Connect system using the ASAPP Media Gateway
Media Gateway: Genesys
Transcribe audio from your Genesys system using the ASAPP Media Gateway
Direct Integration
Direct WebSocket
Use a websocket to send audio directly to AutoTranscribe and receive the transcriptions