AutoTranscribe via Direct Websocket

Use a websocket URL to send audio media to AutoTranscribe

Your organization can use AutoTranscribe to transcribe voice interactions between contact center agents and their customers, in support of a broad range of use cases including analysis, coaching, and quality management.

ASAPP AutoTranscribe is a streaming speech-to-text transcription service that works both with live streams and with audio recordings of completed calls. Integrating your voice system with GenerativeAgent using the AutoTranscribe Websocket enables real-time communication, allowing for seamless interaction between your voice platform and GenerativeAgent’s services.

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.

Some benefits of using Websocket to Stream events include:

• Websocket Connection: Establish a persistent connection between your voice system and the GenerativeAgent server.
• API Streaming: All audio streaming, call signaling, and returned transcripts use a WebSocket API, preceded by an authentication mechanism using a REST API
• Real-time Data Exchange: Messages are exchanged in real time, ensuring quick responses and efficient handling of user queries.
• Bi-directional Communication: Websockets facilitate bi-directional communication, making the interaction smooth and responsive.

Implementation Steps

1. Step 1: Authenticate with ASAPP
2. Step 2: Open a Connection
3. Step 3: Start an Audio Stream
4. Step 4: Send the Audio Stream
5. Step 5: Receive the free-text Transcriptions from AutoTranscribe
6. Step 6: Stop the Audio Stream

Finalize the audio stream when the conversation is over or escalated to a human agent

How it works

1. The API Gateway authenticates customer requests and returns a WebSocket URL, which points to the Voice Gateway with secure protocol.
2. The Voice Gateway validates the client connection request, translates public WebSocket API calls to internal protocols and sends live audio streams to the Speech Recognition Server
3. The Redaction Server redacts the transcribed texts with given customizable redaction rules if redaction is requested.
4. The texts are sent to AutoTransceibe so it can analyze and reply back

This guide covers the WebSocket API solution pattern, which consists of an API Gateway, Voice Gateway, Speech Recognition Server and Redaction Server, where:

Integration Steps

Here’s a high level overview of how to work with AutoTranscribe:

1. Authenticate with ASAPP to gain access to the AutoTranscribe API.
2. Establish a WebSocket connection with the ASAPP Voice Gateway.
3. Send a startStream message with appropriate feature parameters specified.
4. Once the request is accepted by the ASAPP Voice Gateway, stream audio as binary data.
5. The ASAPP voice server will return transcripts in multiple messages.
6. Once the audio streaming is completed, send a finishStream to indicate to the Voice server that there is no more audio to send for this stream request.
7. Upon completion of all audio processing, the server sends a finalResponse which contains a summary of the stream request.

Requirements

Audio Stream Format

In order to be transcribed properly, audio sent to ASAPP AutoTranscribe must be in mono or single-channel for each speaker.

Audio is sent as binary format through the WebSocket; the audio encoding (sample rate and encoding format) should be given in the startStream message.

For real-time live streaming, ASAPP recommends that you stream audio chunk-by-chunk in a real-time streaming format, by sending every 20ms or 100ms of audio as one binary message and sending the next chunk after a 20ms or 100ms interval.

If the chunk is too small, it will require more audio binary messages and more downstream message handling; if the chunk is too big, it increases buffering pressure and slows down the server responsiveness.

Exceptionally large chunks may result in WebSocket transport errors such as timeouts.

When supplying recorded audio to ASAPP for AutoTranscribe model training prior to implementation, send uncompressed .WAV media files with speaker-separated channels.

Recordings for training and real-time streams should have both the same sample rate (8000 samples/sec) and audio encoding (16-bit PCM).

See the Customization section of the AutoTranscribe Product Guide for more on data requirements for transcription model training.

Developer Portal

ASAPP provides an AI Services Developer Portal. Within the portal, developers can do the following:

• Access relevant API documentation (e.g. OpenAPI reference schemas)
• Access API keys for authorization
• Manage user accounts and apps

Visit the Get Started for instructions on creating a developer account, managing teams and apps, and setup for using AI Service APIs.

Step 1 : Authenticate with ASAPP and Obtain an Access URL

All requests to ASAPP sandbox and production APIs must use HTTPS protocol. Traffic using HTTP will not be redirected to HTTPS.

The following HTTPS REST API enables authentication with the ASAPP API Gateway:

• asapp-api-id and asapp-api-secretare required header parameters, both of which will be provided to you by ASAPP.
• A unique conversation ID is recommended to be sent in the request body as externalId. ASAPP refers to this identifier from the client’s system in real-time streaming use cases to redact utterances using context from other utterances in the same conversation (e.g. reference to a credit card in an utterance from 20s earlier). It is the client’s responsibility to ensure externalId is unique.

POST /autotranscribe/v1/streaming-url

Headers (required)

{
    "asapp-api-id": <asapp provided api id>,
    "asapp-api-secret": <asapp provided api secret>
}

Request body (optional)

{
    "externalId": "<unique conversation id>"
}

If the authentication succeeds, a secure WebSocket short-lived access URL will be returned in the HTTP response body. Default TTL (time-to-live) for this URL is 5 minutes.

{
    "streamingUrl": "<short-lived access URL>"
}

Step 2: Open a Connection

Before sending any message, create a WebSocket connection with the access URL obtained from previous step:

wss://<internal-voice-gateway-ingress>?token=<short_lived_access_token>

A WebSocket connection will be established if the short_lived_access_token is validated. Otherwise, the requested connection will be rejected.

Step 3: Start a stream audio message

AutoTranscribe uses the following message sequence for streaming audio, sending transcripts, and ending streamings:

	Send Your Request	Receive ASAPP Response
1	startStream message	startResponse message
2	Stream audio	transcript message
3	finishStream message	finalResponse message

WebSocket protocol request messages in the sequence must be formatted as text (UTF-8 encoded string data); only the audio stream should be formatted in binary. All response messages will also be formatted as text.

Send startStream message

Once the connection is established, send a startStream message with information about the speaker including their role (customer, agent) and their unique identifier (externalId) from your system before sending any audio packets.

{
   "message":"startStream",
   "sender": {
          "role": "customer",
          "externalId": "JD232442"
   }
}

Provide additional optional fields in the startStream message to adjust default transcription settings.

For example, the default language transcription setting is en-US if not denoted in the startStream message. To set the language to Spanish, the language field should be set with value es-US. Once set, AutoTranscribe will expect a Spanish conversation in the audio stream and return transcribed message text in Spanish.

Receive startResponse message

For any startStream message, the server will respond with a startResponse if the request is granted:

{
   "message": "startResponse",
   "streamID": "128342213",
   "status": {
          "code": "1000",
          "description": "OK"
   }
}

The streamID is a unique identifier assigned to the connection by the ASAPP server.

The status code and description may contain additional useful information.

If there is an application status code error with the request, the ASAPP server sends a finalResponse message with an error description, and the server then closes the connection.

Step 4: Send the audio stream

You can start to stream audio as soon as the startStream message is sent without the need to wait for the startResponse. However, it is possible a request could be rejected either due to an invalid startStream or internal server errors. If that is the case, the server notifies with a finalResponse message, and any streamed audio packets will be dropped by the server.

Audio must be sent as binary data of WebSocket protocol:

ws.send(<binary_blob>)

The server does not acknowledge receiving individual audio packets. The summary in the finalResponse message can be used to verify if any audio packet was not received by the server.

If audio can be transcribed, the server sends back transcript messages asynchronously.

For real-time live streaming, it is recommeneded that audio streams are sent chunk-by-chunk, sending every 20ms or 100ms of audio as one binary message. Exceptionally large chunks may result in WebSocket transport errors such as timeouts.

Receive transcript messages

The server sends back the transcript message, which contains one complete utterance.

Example of a transcript message:

{
   "message": "transcript",
   "start": 0,
   "end": 1000,
   "utterance":
   [
      {"text": "Hi, my ID is 123."}
   ]
}

Step 5: Receive Transcriptions from AutoTranscribe

Now you must call GET /messages to receive all the transcript messages for a completed call.

Conversation transcripts are available for seven days after they are completed.

curl -X GET 'https://api.sandbox.asapp.com/conversation/v1/conversation/messages' \
--header 'asapp-api-id: <API KEY ID>' \
--header 'asapp-api-secret: <API TOKEN>' \
--header 'Content-Type: application/json' \
--data '{
    "externalId": "Your GUID/UCID of the SPIREC Call"
}'

A Succesful response returns a 200 and the Call Transcripts

{
  "type": "transcript",
  "externalConversationId": "<guid>",
  "streamId": "<streamId>",
  "sender": {
    "externalId": "<id>",
    "role": "customer",  // or "agent"
  },
  "autotranscribeResponse": {
    "message": "transcript",
    "start": 0,
    "end": 1000,
    "utterance": [
       {"text": "<transcript text>"}
      ]
  }
}

Step 6: Stop the streaming audio message

Send finishStream message

When the audio stream is complete, send a finishStream message. Any audio message sent after finishStream will be dropped by the service.

{
   "message": "finishStream"
}

Any other non-audio messages sent after finishStream will be dropped, the service will send a finalResponse with error code 4056 (Wrong message order) and the connection will be closed.

Receive finalResponse message

The server sends a finalResponse at the end of the streaming session and closes the connection, after which the server will stop processing incoming messages for the stream. It is safe to close the WebSocket connection when the finalResponse message is received.

The server will end a given stream session if any of following are true:

• Server receives finishStream and all audio received has been processed
• Server detects connection idle timeout (at 60 seconds)
• Server internal errors (unable to recover)
• Request message is invalid (note: if the access token is invalid, the WebSocket will close with a WebSocket error code)
• Critical requested feature is not supported, for example, redaction
• Service maintenance
• Streaming duration over limit (default is 3 hours)

In case of non-application WebSocket errors, the WebSocket layer closes the connection, and the server may not get an opportunity to send a finalResponse message.

The finalResponsemessage has a summary of the stream along with the status code, which you can use to verify if there are any missing audio packets or transcript messages:

{
   "message": "finalResponse",
   "streamId": "128342213",
   "status": {
       "code": "1000",
       "description": "OK"
   },
   "summary": {
       "totalAudioBytes": 300,     // number of audio bytes received 
       "audioDurationMs": 6000,    // audio length in milliseconds processed by the server
       "streamingSeconds": 6,
       "transcripts": 10     // number of transcripts recognized
}

Fields & Parameters

StartStream Request Fields

Field	Description	Default	Supported Values
sender.role (required)	A participant role, usually the customer or an agent for human participants.	n/a	“agent”, “customer”
sender.externalId (required)	Participant ID from the external system, it should be the same for all interactions of the same individual	n/a	“BL2341334”
language	IETF language tag	en-US	“en-US”, “es-US”
samplingRate	Audio samples/sec	8000	8000
encoding	‘L16’: PCM data with 16 bit/sample	L16	“L16”
smartFormatting	Request for post processing: Inverse Text Normalization (convert spoken form to written form), e.g., ‘twenty two —> 22’. Auto punctuation and capitalization	true	true, false
detailedToken	If true, outputs word-level details like word content, timestamp and word type.	false	true, false
audioRecordingAllowed	false: ASAPP will not record the audio; true: ASAPP may record and store the audio for this conversation	false	true, false
redactionOutput	If detailedToken is true along with value ‘redacted’ or ‘redacted_and_unredacted’, request will be rejected. If no redaction rules configured by the client for ‘redacted’ or ‘redacted_and_unredacted’, the request will be rejected. If smartFormatting is False, requests with value ‘redacted’ or ‘redacted_and_unredacted’ will be rejected.	redacted	“redacted”, “unredacted”,“redacted_and_unredacted”

Transcript Message Response Fields

Field	Description	Format	Example Syntax
start	Start time (millisecond) of the utterance (in milliseconds) relative to the start of the audio input	integer	0
end	End time (millisecond) of the utterance (in milliseconds) relative to the start of the audio input	integer	300
utterance.text	The written text of the utterance. While an utterance can have multiple alternatives (e.g., ‘me two’ vs. ‘me too’) ASAPP provides only the most probable alternative only, based on model prediction confidence.	array	“Hi, my ID is 123.”

If the detailedToken in startStream request is set to true, additional fields are provided within the utterance array for each token:

Field	Description	Format	Example Syntax
token.content	Text or punctuation	string	“is”, ”?”
token.start	Start time (millisecond) of the token relative to the start of the audio input	integer	170
token.end	End time (millisecond) audio boundary of the token relative to the start of the audio input, there may be silence after that, so it does not necessarily match with the startMs of the next token.	integer	200
token.punctuationAfter	Optional, punctuation attached after the content	string	’.’
token.punctuationBefore	Optional, punctuation attached in front of the content	string	’“’

Custom Vocabulary

The ASAPP speech server can boost specific word accuracy if a target list of vocabulary words is provided before recognition starts, using an updateVocabulary message.

The updateVocabulary service can be sent multiple times during a session. Vocabulary is additive, which means the new vocabulary words are appended to the previous ones. If vocabulary is sent in between sent audio packets, it will take into effect only after the end of the current utterance being processed.

All updateVocabulary changes are valid only for the current WebSocket session.

The following fields are part of a updateVocabulary message:

Field	Description	Mandatory	Example Syntax
phrase	Phrase which needs to be boosted. Prevent adding longer phrases, instead add them as separate entries.	Yes	“IEEE”
soundsLike	This provides the ways in which a phrase can be said/pronounced. Certain rules: - Spell out numbers (25 -> ‘two five’ and/or ‘twenty five’) - Spell out acronyms (WHO -> ‘w h o’) - Use lowercase letters for everything - Limit phrases to English and Spanish-language letters (accented consonants and vowels accepted)	No	“i triple e”
category	Supported Categories: ‘address’, ‘name’, ‘number’. Categories help the AutoTranscribe service normalize the provided phrase so it can guess certain ways in which a phrase can be pronounced. e.g., ‘717 N Blvd’ with ‘address’ category will help the service normalize the phrase to ‘seven one seven North Boulevard’	No	“address”, “name”, “number”, “company”, “currency”

Example request and response:

Request

{
    "message": "updateVocabulary",
    "phrases":
    [
        {
            "phrase": "IEEE",
            "category": "company",
            "soundsLike":
            [
                "I triple E"
            ]
        },
        {
            "phrase": "25.00",
            "category": "currency",
            "soundsLike":
            [
                "twenty five dollars"
            ]
        },
        {
            "phrase": "HHilton",
            "category": "company",
            "soundsLike":
            [
                "H Hilton",
                "Hilton Honors"
            ]
        },
        {
            "phrase": "Jon Snow",
            "category": "name",
            "soundsLike":
            [
                "John Snow"
            ],
        },
        {
            "phrase": "717 N Shoreline Blvd",
            "category": "address"
        }
    ]
}

Response

{
   "message": "vocabularyResponse",
   "status": {
    "code": "1000",
    "description": "OK"
}

Application Status Codes

Status code	Description
1000	OK
1008	Invalid or expired access token
2002	Error in fetching conversationId. This error code is only possible when integration with other AI Services is enabled
4040	Message format incorrect
4050	Language not supported
4051	Encoding not supported
4053	Sample rate not supported
4056	Wrong message order or missing required message
4080	Unable to transcribe the audio
4082	Audio decode failure
4083	Connection idle timeout. Try streaming audio in real-time
4084	Custom vocabulary phrase exceeds limit
4090	Streaming duration over limit
4091	Invalid vocabulary format
4092	Redact only smart formatted text
4093	Redaction only supported if detailedTokens in True
4094	RedactionOutput cannot be unredacted or redacted_and_unredacted because of global config being to always redact
5000	Internal service error
5001	Service shutting down
5002	No instances available

Retrieving Transcript Data

In addition to real-time transcription messages via WebSocket, AutoTranscribe also can output transcripts through two other mechanisms:

• After-call: GET endpoint responds to your requests for a designated call with the full set of utterances from that completed conversation
• Batch: File Exporter service responds to your request for a designated time interval with a link to a data feed file that includes all utterances from that interval’s conversations

After-Call via GET Request

GET /conversation/v1/conversation/messages

Use this endpoint to retrieve all the transcript messages for a completed call.

When to Call

Once the conversation is complete. Conversation transcripts are available for seven days after they are completed.

Request Details

Requests must include a call identifier with the GUID/UCID of the SIPREC call.

Response Details

When successful, this endpoint responds with an array of objects, each of which corresponds to a single message. Each object contains the text of the message, the sender’s role and identifier, a unique message identifier, and timestamps.

Message Limit

This endpoint will respond with up to 1,000 transcribed messages per conversation, approximately a two-hour continuous call. All messages are received in a single response without any pagination.

To retrieve all messages for calls that exceed this limit, use either a real-time mechanism or File Exporter for transcript retrieval.

Batch via File Exporter

AutoTranscribe makes full transcripts for batches of calls available using the File Exporter service’s utterances data feed.

The File Exporter service is meant to be used as a batch mechanism for exporting data to your data warehouse, either on a scheduled basis (e.g. nightly, weekly) or for ad hoc analyses. Data that populates feeds for the File Exporter service updates once daily at 2:00AM UTC.

Visit Retrieving Data for AI Services for a guide on how to interact with the File Exporter service.