Twilio Changelog | Jan. 13, 2025

Send Real-Time Transcripts to Voice Intelligence

Customers generating a Real-Time Transcript for Voice calls can now send these transcripts to Twilio Voice Intelligence for integrated post-call processing. This feature enables you to extract actionable insights at scale by storing and analyzing transcripts initially generated in real-time.

Here’s what you can do:

  1. Persist Live Transcripts: Automatically store real-time transcriptions in Voice Intelligence’s historical log for future reference and analysis.

  2. Run Post-Call Language Operators: Trigger configured Language Operators in Voice Intelligence to generate AI-powered insights and automate actions after the call has concluded. 

This integration with Voice Intelligence can be configured either through the <Transcription> TwiML verb or through the Real-Time Transcription API. It works seamlessly alongside the existing live processing Webhook setting (statusCallbackURL), which streams utterance-level data to your app during the call.

To enable this, include the intelligenceService parameter (Voice Intelligence Service SID) when starting a transcription session. If you don’t have a Voice Intelligence Service yet, create one in Console.

Via <Transcription> TwiML verb:

<?xml version="1.0" encoding="UTF-8"?>
<Response>
    <Start>
        <Transcription 
          intelligenceService="GAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"                    
          statusCallbackUrl="https://example.com/your-callback-url" />
    </Start>
</Response>
curl -X POST "https://api.twilio.com/2010-04-01/Accounts/$TWILIO_ACCOUNT_SID/Calls/CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/Transcriptions.json" \
--data-urlencode "IntelligenceService=GAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" \
--data-urlencode "StatusCallbackUrl=https://example.com/your-callback-url" \
-u $TWILIO_ACCOUNT_SID:$TWILIO_AUTH_TOKEN

Note: To use Post-Call Language Operators with real-time transcripts, ensure these Operators are configured in your Voice Intelligence Service before starting the transcription session. Language Operators are executed after the Real-Time Transcription session concludes, either automatically through the call ending or manually by stopping the live transcription.

For more details on how to get started with Real-Time Transcription, check out our TwiML and  API documentation.

Additional Resources

Blog

Read more about our latest product updates, product tutorials, and community projects.


Docs

See API reference documentation, quickstarts, SDKs, and multi-language code samples.

Events

Find upcoming events and join us virtually or in person to learn more about our products.