Real-time stateless dictation

Overview

The WebSocket Secure (WSS) /transcribe API enables real-time, bidirectional communication with the Corti system for stateless speech to text. Clients can send and receive structured data, including transcripts and detected commands. This documentation provides a comprehensive guide for integrating these capabilities.

This /transcribe endpoint supports real-time stateless dictation.

If you are looking for real-time ambient documentation interactions, you should use the /streams WSS
If you are looking for transcript generation based on a pre-recorded audio file, then please refer to the /transcripts endpoint

1. Establishing a Connection

Clients must initiate a WebSocket connection using the wss:// scheme.

The authentication for the WSS streams requires in addition to the tenant-name parameter a token parameter to pass in the Bearer access token.

Query Parameters

environment

enum

required

eu or us

tenant-name

string

required

Specifies the tenant context

token

string

required

Bearer $token

import { CortiClient } from "@corti/sdk";

const client = new CortiClient({
  auth: {
    accessToken: "<ACCESS_TOKEN_FROM_YOUR_BACKEND>",
  },
});

curl --request GET \
  --url "wss://api.$environment.corti.app/audio-bridge/v2/transcribe?tenant-name=$tenant&token=Bearer%20$accessToken"

2. Handshake Response

101 Switching Protocols

Indicates a successful WebSocket connection. Upon successful connection, send a config message to define the configuration: Specify the input language and expected output preferences.

The config message must be sent within 10 seconds of the web socket being opened to prevent CONFIG-TIMEOUT, which will require establishing a new wss connection.

3. Sending Messages

Configuration

Declare your /transcribe configuration using the message "type": "config" followed by defining the "configuration": {<config details, per options below>}. Defining the type is required along with the primaryLanguage configuration parameter. The other parameters are optional for use, depending on your need and workflow.

Configuration notes:

Clients must send a streams configuration message and wait for a response of type CONFIG_ACCEPTED before transmitting other data.
If the configuration is not valid it will return CONFIG_DENIED.
The configuration must be committed within 10 seconds of opening the WebSocket, else it will time-out with CONFIG_TIMEOUT.

type

string

default:"config"

required

configuration

object

required

Hide child attributes

primaryLanguage

string

required

The locale of the primary spoken language. See supported languages codes and more information here.

interimResults

bool

When true, interim (preview) transcript results ("isFinal"=false) will be returned with lower latency than final transcript results.

spokenPunctuation

bool

When true, converts spoken punctuation such as period or slash into .or /. Read more about supported punctuation here.

automaticPunctuation

bool

When true, automatically punctuates and capitalizes in the final transcript.

Spoken and Automatic Punctuation are mutually exclusive - only one should be set to true in a given configuration request. If both are included and set to true, then spokenPunctuation will take precedence and override automaticPunctuation.

commands

object

Provide the commands that should be registered and detected - Read more about commands here.

Show child attributes

string

required

Unique value to identify the command. This, along with the command phrase, will be returned by the API when the command is recognized during dictation.

phrases

string[]

required

One or more word sequence(s) that can be spoken to trigger the command. At least one phrase is required per command.

variables

object

Placeholders that can (optionally) be added in phrases to define multiple words that should trigger the command.

Show child attributes

key

string

required

Define the variable used in command phrase here.

type

enum

required

The only variable type supported at this time is enum.

enum

string[]

required

List of values that should be recognized for the defined variable.

formatting

object

Define each type of formatting preferences using the enum options described below. Formatting configuration is optional, and when no properties are configured, the values listed as default will be applied automatically.

Read more about formatting options, including how localization is handled with detailed examples per language, here.

Show child attributes

dates

enum

Option	Format	Example
`as_dictated`	As dictated	”February third twenty twenty five" "February third" "February twenty twenty five”
`locale:long`	Long date	”February 3, 2025" "February 3" "February 2025”
`locale:medium`	Medium date	”Feb 3, 2025" "Feb 3" "Feb 2025”
`locale:short`	Short date	”2/3/25" "2/3" "2/2025”
`iso`	ISO 8601	”2025-02-03" "02-03" "2025-02”

times

enum

Option	Format	Example
`as_dictated`	As dictated	”Eight o’clock" "half past eight" "eight thirty six PM”
`locale`	12 or 24-hour, depending on `primaryLanguage` defined in config	”8:00 AM” or “08:00" "8:30 AM” or “08:30" "8:36 PM” or “20:36”
`h24`	24-hour	”08:00" "08:30" "20:36”
`h12`	12-hour	”8:00 AM" "8:30 AM" "8:36 PM”

numbers

enum

Option	Format	Example
`as_dictated`	As dictated	”one, two, … nine, ten, eleven, twelve
`numerals_above_nine`	Single digit as words, multi-digit as number	”One, two … nine, 10, 11, 12”
`numerals`	Numbers only	”1, 2, … 9, 10, 11, 12”

Localization of numbers applied automatically for thousands and decimal separators

measurements

enum

Option	Format	Example	Default
`as_dictated`	As dictated	”Millimeters, centimeters, inches; Blood pressure one twenty over eighty”
`abbreviated`	Abbreviated	”mm, cm, in; BP 120/80”

Click here to see a full list of supported units and measurements

numericRanges

enum

Option	Format	Example	Default
`as_dictated`	As dictated	”one to ten”
`numerals`	As numbers	”1-10”

ordinals

enum

Option	Format	Example
`as_dictated`	As dictated	”First, second, third”
`numerals_above_nine`	First through ninth as words, multi-digit as number	”First, second … ninth, 10th, 11th, 12th”
`numerals`	Abbreviated	”1st, 2nd, 3rd”

audioFormat

string

Define the audio format of the incoming audio stream - optional but recommended.

When omitted, the server auto-detects the format from the first audio chunk using ffprobe. Supported audio will be processed. Unsupported return an error but might in some cases error silently.
If provided (recommended), the provided MIME type must be supported and the audio must match the MIME type. An unsupported MIME type results in CONFIG_REJECTED. Audio that differs from the MIME type will return audio validation errors on the socket.

See more about supported formats here.

Example

Here is an example configuration for transcription of dictated audio in English with spoken punctuation enabled, two commands defined, and (default) formatting options defined:

{
  "type": "config",
  "configuration":{
    "primaryLanguage": "en",
    "interimResults": true,
    "spokenPunctuation": true, 
    "commands": [
      {
        "id": "next_section",
        "phrases": [
          "next section", "go to next section"
        ]
      },
      {
        "id": "insert_template",
        "phrases": [
          "insert my {template_name} template", "insert {template_name} template"
        ],
        "variables": [
          {
            "key": "template_name",
            "type": "enum",
            "enum": [
              "soap", "radiology", "referral"
            ]
          }
        ]
      }
    ],
    "formatting": {
      "dates": "locale:long",
      "times": "locale",
      "numbers": "numerals_above_nine",
      "measurements": "abbreviated",
      "numericRanges": "numerals",
      "ordinals": "numerals_above_nine"
    },
    "audioFormat": "audio/ogg"
  }
}

Sending Audio

Ensure that your configuration was accepted before sending audio, and that the initial audio chunk is not too small as it needs to contain the headers to properly decode the audio.We recommend sending audio in chunks of 250-500ms. In terms of buffering, the limit is 64000 bytes per chunk.Audio data should be sent as raw binary without JSON wrapping.

A variety of common audio formats are supported; audio will be passed through a transcoder before speech-to-text processing. Similarly, specification of sample rate, depth or other audio settings is not required at this time. See more details on supported audio formats here.

transcribeSocket.sendAudio(audioChunk); // method doesn't do the chunking

Flush the Audio Buffer

To flush the audio buffer, forcing transcript segments and detected commands to be returned over the web socket (e.g., when turning off or muting the microphone in a “hold-to-talk” dictation workflow, or in applications that support mic “go to sleep”), send a message -

{
  "type":"flush"
}

The server will return text/commands for audio sent before the flush message and then respond with messages -

{
  "type": "flushed"
}

{
  "type": "delta_usage",
  "credits": 0.00116
}

Delta usage represents incremental credit consumption between recording initiation and flush events. Delta usage is approximate and may differ slightly from final usage sent after end message is processed (see below). Final, end session usage will be reflected in API billing. The web socket will remain open after flush processing so dictation can continue.

Client side considerations:¹ If you rely on a flush event to separate data (e.g., for different sections in an EHR template), then be sure to receive the flushed event before moving on to the next data field.² When using a web browser MediaRecorder API, audio is buffered and only emitted at the configured timeslice interval. Therefore, before sending a flush message, call MediaRecorder.requestData() to force any remaining buffered audio on the client to be transmitted to the server. This ensures all audio reaches the server before the flush is processed.

Ending the Session

To end the /transcribe session, send a message -

{
  "type": "end"
}

This will signal the server to send any remaining transcript segments and/or detected commands. Then, the server will send two messages -

{
  "type": "usage",
  "credits": 0.1
}

{
  "type": "ended"
}

Following the message type ended, the server will close the web socket.

4. Responses

Configuration

type

string

default:"CONFIG_ACCEPTED"

required

Returned when sending a valid configuration.

sessionId

uuid

required

Returned when sending a valid configuration.

configuration

object

The resolved configuration, including accepted client-defined values and server-applied defaults for parameters not defined in client configuration.

Transcripts

type

string

default:"transcript"

required

data

string

required

Show child attributes

text

string

required

Transcript segment with punctuations applied and command phrases removed

rawTranscriptText

string

The raw transcript without spoken punctuation applied and without command phrases removed

start

float64

Start time of the transcript segment in seconds

end

float64

End time of the transcript segment in seconds

isFinal

bool

required

If false, then interim transcript result

Transcript response

{
    "type": "transcript",
    "data": {
        "text": "patient reports mild chest pain.",
        "rawTranscriptText": "patient reports mild chest pain period",
        "start": 0.0,
        "end": 3.2,
        "isFinal": true
    }
}

Click here for detailed guide on how to properly insert transcript segments with proper handling of whitespace, interim vs. final results, and text vs. rawTranscriptText fields.

Commands

type

string

default:"command"

required

data

string

required

Show child attributes

string

required

To identify the command when it gets detected and returned over the WebSocket

variables

string[]

The variables identified

rawTranscriptText

string

The raw transcript without spoken punctuation applied and without command phrases removed

start

float64

Start time of the transcript segment in seconds

end

float64

End time of the transcript segment in seconds

Command response

{
  "type": "command",
  "data": {
    "id": "insert_template",
    "variables": {
      "template_name": "radiology"
    },
    "rawTranscriptText": "insert my radiology template",
    "start": 2.3,
    "end": 2.9
  }
}

Flushed

type

string

default:"flushed"

required

Returned by server, after processing flush event from client, to return transcript segments/ detected commands

{
  "type": "flushed"
}

Usage

type

string

default:"delta-usage"

Returned by server, after processing flush event from client, to convey amount of credits consumed since recording started. Delta usage is approximate and may differ slightly from final usage sent after end message is processed.

{
  "type": "delta_usage",
  "credits": 0.00116
}

type

string

default:"usage"

Returned by server, after processing end event from client, to convey amount of credits consumed

{
  "type": "usage",
  "credits": 0.1
}

Ended

type

string

default:"ended"

required

Returned by server, after processing end event from client, before closing the web socket

{
  "type": "ended"
}

socket.on("message", (msg) => {
    switch (msg.type) {
        case "transcript":
            console.log("Transcript:", msg.data.text, "final:", msg.data.isFinal);
            break;
        case "command":
            console.log("Command:", msg.data.id, msg.data.variables);
            break;
        case "flushed":
            console.log("Flush complete");
            break;
        case "ended":
            console.log("Session ended");
            socket.close();
            break;
        case "usage":
            console.log("Credits used:", msg.credits);
            break;
        case "error":
            console.error("Server error:", msg.error);
            break;
    }
});

5. Error Handling

type

string

required

Returned when sending an invalid configuration.Possible errors: CONFIG_DENIED, CONFIG_TIMEOUT, CONFIG_ALREADY_RECEIVED, CONFIG_MISSING

reason

string

The reason the configuration is invalid.

sessionId

uuid

required

The session ID.

Once configuration has been accepted and the session is running, you may encounter runtime or application-level errors. These are sent as JSON objects with the following structure:

{
  "type": "error",
  "error": {
    "id": "error id",
    "title": "error title",
    "status": 400,
    "details": "error details",
    "doc":"link to documentation"
  }
}

Handle errors in SDK

With the recommended approach (passing configuration as part of connect), configuration errors are raised during connect (the call fails). Runtime errors are emitted via the error event; you can also inspect the original message in the message handler.

try {
    const socket = await client.transcribe.connect({
        configuration: {
            primaryLanguage: "en",
            automaticPunctuation: true,
        },
    });

    socket.on("error", (err) => {
        // Network errors and reconnect failures
        console.error("Socket error:", err.message);
    });

    socket.on("message", (msg) => {
        if (msg.type === "error") {
            // Server-sent runtime error
            console.error("Server error:", msg.error);
        }
    });
} catch (err) {
    // CONFIG_DENIED, CONFIG_TIMEOUT, or connection failure
    console.error("Connect failed:", err.message);
}

Web Socket APIs

REST APIs

Agentic APIs (beta)

Admin APIs

Overview

1. Establishing a Connection

Query Parameters

2. Handshake Response

101 Switching Protocols

3. Sending Messages

Configuration

Example

Sending Audio

Flush the Audio Buffer

Ending the Session

4. Responses

Configuration

Transcripts

Commands

Flushed

Usage

Ended

5. Error Handling

Handle errors in SDK

Web Socket APIs

REST APIs

Agentic APIs (beta)

Admin APIs

​Overview

​1. Establishing a Connection

​Query Parameters

​2. Handshake Response

​101 Switching Protocols

​3. Sending Messages

​Configuration

​Example

​Sending Audio

​Flush the Audio Buffer

​Ending the Session

​4. Responses

​Configuration

​Transcripts

​Commands

​Flushed

​Usage

​Ended

​Subscribe to messages in SDK

​5. Error Handling

​Handle errors in SDK

Overview

1. Establishing a Connection

Query Parameters

2. Handshake Response

101 Switching Protocols

3. Sending Messages

Configuration

Example

Sending Audio

Flush the Audio Buffer

Ending the Session

4. Responses

Configuration

Transcripts

Commands

Flushed

Usage

Ended

Subscribe to messages in SDK

5. Error Handling

Handle errors in SDK