Calls Transcriptions subresource
Legal notice
Real-Time Transcriptions, including the <Transcriptions> TwiML noun and API, use artificial intelligence or machine learning technologies. By enabling or using any of the features or functionalities within Programmable Voice that are identified as using artificial intelligence or machine learning technology, you acknowledge and agree that your use of these features or functionalities is subject to the terms of the Predictive and Generative AI/ML Features Addendum.
Transcriptions is a subresource of Calls and represents a real-time audio transcription during a live call. You can start and stop a transcription on any in-progress call via API or via the <Transcription> TwiML Noun.
- To start a real-time transcription on a live call, create a Transcription.
- To stop a real-time transcription, update a Transcription status.
The SID of the Transcription resource.
^GT[0-9a-fA-F]{32}$Min length: 34Max length: 34The SID of the Account that created this Transcription resource.
^AC[0-9a-fA-F]{32}$Min length: 34Max length: 34The SID of the Call the Transcription resource is associated with.
^CA[0-9a-fA-F]{32}$Min length: 34Max length: 34The user-specified name of this Transcription, if one was given when the Transcription was created. This may be used to stop the Transcription.
The status - one of stopped, in-flight
in-progressstoppedThe date and time in GMT that this resource was last updated, specified in RFC 2822 format.
POST https://api.twilio.com/2010-04-01/Accounts/{AccountSid}/Calls/{CallSid}/Transcriptions.json
The SID of the Account that created this Transcription resource.
^AC[0-9a-fA-F]{32}$Min length: 34Max length: 34application/x-www-form-urlencodedThe user-specified name of this Transcription, if one was given when the Transcription was created. This may be used to stop the Transcription.
The http method for the status_callback (one of GET, POST).
GETPOSTIndicates if partial results are going to be sent to the customer
Language code used by the transcription engine, specified in BCP-47 format
Definition of the transcription engine to be used, among those supported by Twilio
indicates if the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks
Recognition model used by the transcription engine, among those supported by the provider
A Phrase contains words and phrase "hints" so that the speech recognition engine is more likely to recognize them.
The provider will add punctuation to recognition result
The SID or unique name of the Intelligence Service for persisting transcripts and running post-call Language Operators .
1// Download the helper library from https://www.twilio.com/docs/node/install2const twilio = require("twilio"); // Or, for ESM: import twilio from "twilio";34// Find your Account SID and Auth Token at twilio.com/console5// and set the environment variables. See http://twil.io/secure6const accountSid = process.env.TWILIO_ACCOUNT_SID;7const authToken = process.env.TWILIO_AUTH_TOKEN;8const client = twilio(accountSid, authToken);910async function createRealtimeTranscription() {11const transcription = await client12.calls("CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")13.transcriptions.create();1415console.log(transcription.sid);16}1718createRealtimeTranscription();
Response
1{2"account_sid": "ACaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",3"call_sid": "CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",4"sid": "GTaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",5"name": null,6"status": "in-progress",7"date_updated": "Thu, 30 Jul 2015 20:00:00 +0000",8"uri": "/2010-04-01/Accounts/ACaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/Calls/CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/Transcriptions/GTaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa.json"9}
POST https://api.twilio.com/2010-04-01/Accounts/{AccountSid}/Calls/{CallSid}/Transcriptions/{Sid}.json
The SID of the Account that created this Transcription resource.
^AC[0-9a-fA-F]{32}$Min length: 34Max length: 34The SID of the Call the Transcription resource is associated with.
^CA[0-9a-fA-F]{32}$Min length: 34Max length: 34The SID of the Transcription resource, or the name used when creating the resource
application/x-www-form-urlencodedstoppedYou can stop an in-progress Transcription by updating the status to stopped. You can also use TwiML to stop a Transcription.
When making this request, you can use the Transcription subresource's SID or the name (if one was given when the Transcription was created).
1// Download the helper library from https://www.twilio.com/docs/node/install2const twilio = require("twilio"); // Or, for ESM: import twilio from "twilio";34// Find your Account SID and Auth Token at twilio.com/console5// and set the environment variables. See http://twil.io/secure6const accountSid = process.env.TWILIO_ACCOUNT_SID;7const authToken = process.env.TWILIO_AUTH_TOKEN;8const client = twilio(accountSid, authToken);910async function updateRealtimeTranscription() {11const transcription = await client12.calls("CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")13.transcriptions("GTaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")14.update({ status: "stopped" });1516console.log(transcription.sid);17}1819updateRealtimeTranscription();
Response
1{2"account_sid": "ACaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",3"call_sid": "CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",4"sid": "GTaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",5"name": null,6"status": "stopped",7"date_updated": "Thu, 30 Jul 2015 20:00:00 +0000",8"uri": "/2010-04-01/Accounts/ACaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/Calls/CAaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/Transcriptions/GTaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa.json"9}
HIPAA eligibility and PCI compliance varies depending on your selected speech model and whether you use webhooks or persisted transcripts. To determine whether your implementation may be HIPAA eligible or PCI compliant, see the following table.
| Transcription engine | Speech model | Transcript destination | HIPAA eligibility | PCI-compliant |
|---|---|---|---|---|
| Any supported model | Webhooks | Yes | Yes | |
| Any supported model | Persisted Transcript | Yes | No | |
| Deepgram | nova-2 or nova-3 monolingual variants | Webhooks | Yes | Yes |
| Deepgram | nova-2 or nova-3 monolingual variants | Persisted Transcript | Yes | No |
| Deepgram | nova-3 multilingual | Webhooks or Persisted Transcript | No | No |
AI Nutrition Facts
The Calls Transcriptions subresource and <Transcriptions> TwiML noun use third-party artificial technology and machine learning technologies.
Twilio's AI Nutrition Facts provide an overview of the AI feature you're using, so you can better understand how the AI is working with your data. Real-Time Transcriptions AI qualities are outlined in the following Speech to Text Transcriptions - Programmable Voice Nutrition Facts label. For more information and the glossary regarding the AI Nutrition Facts Label, see Twilio's AI Nutrition Facts.
AI Nutrition Facts
Speech to Text Transcriptions - Programmable Voice, Twilio Video, and Conversational Intelligence
- Description
- Generate speech to text voice transcriptions (real-time and post-call) in Programmable Voice, Twilio Video, and Conversational Intelligence.
- Privacy Ladder Level
- N/A
- Feature is Optional
- Yes
- Model Type
- Generative and Predictive - Automatic Speech Recognition
- Base Model
- Deepgram Speech-to-Text, Google Speech-to-Text, Amazon Transcribe
- Base Model Trained with Customer Data
- No
- Customer Data is Shared with Model Vendor
- No
- Training Data Anonymized
- N/A
- Data Deletion
- Yes
- Human in the Loop
- Yes
- Data Retention
- Until the customer deletes
- Logging & Auditing
- Yes
- Guardrails
- Yes
- Input/Output Consistency
- Yes
- Other Resources
- https://www.twilio.com/docs/conversational-intelligence
Trust Ingredients
Conversational Intelligence, Programmable Voice, and Twilio Video only use the default Base Model provided by the Model Vendor. The Base Model is not trained using customer data.
Conversational Intelligence, Programmable Voice, and Twilio Video only use the default Base Model provided by the Model Vendor. The Base Model is not trained using customer data.
Base Model is not trained using any customer data.
Transcriptions are deleted by the customer using the Conversational Intelligence API or when a customer account is deprovisioned.
The customer views output in the Conversational Intelligence API or Transcript Viewer.
Compliance
The customer can listen to the input (recording) and view the output (transcript).
The customer can listen to the input (recording) and view the output (transcript).
The customer is responsible for human review.
Learn more about this label at nutrition-facts.ai