Transcribe - Cognigy Documentation

Transcribe

The transcribe verb generates real-time transcriptions of speech. This verb can be nested only within the following verbs:

dial
listen

When nested within a dial verb, transcribe provides long-running transcription of a phone call.

Dial Example

{
  "verb": "dial",
  "actionHook": "dial",
  "callerId": "+491173331212",
  "answerOnBridge": true,
  "dtmfCapture": ["*2", "*3"],
  "dtmfHook": {
    "url": "/dtmf",
    "method": "GET"
  },
  "amd": {
    "actionHook": "amd",
    "recognizer": {
      "vendor": "microsoft",
      "language": "en-US"
    }
  },
  "transcribe": {
    "transcriptionHook": "http://example.com/transcribe",
    "recognizer": {
      "vendor": "Google",
      "language": "en-US",
      "interim": true
    }
  },
  "target": [
    {
      "type": "phone",
      "number": "+49XXXXXXXXXXX",
      "trunk": "Twilio"
    },
    {
      "type": "sip",
      "sipUri": "sip:49XXXXXXXXXXX@sip.myTrunk.com",
      "auth": {
        "username": "John",
        "password": "Doe"
      }
    },
    {
      "type": "user",
      "name": "jane@sip.example.com"
    }
  ]
}

When nested within a listen verb, transcribe provides a transcription of recorded messages, such as voicemail.

Listen Example

{
  "verb": "listen",
  "url": "wss://myrecorder.example.com/calls",
  "mixType": "stereo",
  "transcribe": {
    "transcriptionHook": "http://example.com/transcribe",
    "recognizer": {
      "vendor": "Google",
      "language": "en-US",
      "interim": true
    }
  }
}

Configuration

The following table lists the available parameters:

Parameter	Type	Description	Required
transcriptionHook	string	A webhook URL where the system sends an HTTP POST whenever a partial or final transcription result is available from the provider. This allows your application to process or store transcripts in real time.	Yes
translationHook	string	A webhook URL where the system sends an HTTP POST whenever a translation of the transcribed text is available. Only used if translation is enabled. Useful for multilanguage workflows.	No
recognizer	object	Contains configuration options for the speech recognition engine. This includes language selection, hints, diarization, and other advanced settings.	No
recognizer.vendor	string	The speech recognition provider to use, for example, Google, Amazon, or Azure. The vendor determines transcription quality, supported languages, and feature availability.	Yes
recognizer.label	string	A custom label to identify this recognizer instance in logs or dashboards. Helpful when multiple recognizers are configured.	No
recognizer.language	string	The primary language code for transcription, for example, `en-US` for English, `fr-FR` for French. Determines how speech is interpreted.	No
recognizer.hints	array	An array of words or phrases that may appear in the audio and should be recognized more accurately. Useful for domain-specific terms, names, or technical vocabulary.	No
recognizer.hintsBoost	number	A numeric value specifying how strongly the recognizer should prioritize the hint words. Higher numbers give stronger emphasis, improving accuracy for key terms.	No
recognizer.altLanguages	array	An array of additional language codes that the recognizer can use for multilingual audio. Allows recognition of mixed-language content.	No
recognizer.profanityFilter	boolean	If `true`, the recognizer will automatically remove or mask profanity from the transcription output.	No
recognizer.interim	boolean	If `true`, returns partial transcription results as the audio is being processed. Useful for live captions or real-time feedback.	No
recognizer.punctuation	boolean	If `true`, punctuation marks, for example, periods or commas, are included in the transcription to improve readability.	No
recognizer.diarization	boolean	If `true`, enables speaker diarization, which assigns segments of the transcript to individual speakers.	No
recognizer.diarizationMinSpeakers	number	The minimum number of speakers expected in the audio. Helps the diarization algorithm distinguish between speakers accurately.	No
recognizer.diarizationMaxSpeakers	number	The maximum number of speakers expected in the audio. Prevents the algorithm from splitting speech unnecessarily.	No
recognizer.vad	object	Voice Activity Detection settings. Determines how the system detects when someone is speaking vs. silence, improving transcription timing and accuracy.	No
recognizer.fallbackVendor	string	Specifies an alternative transcription vendor to use if the primary vendor fails. Ensures reliability in critical workflows.	No
recognizer.fallbackLanguage	string	Language code to use for the fallback vendor. Must match a language supported by the fallback provider.	No
earlyMedia	boolean	If `true`, transcription starts as soon as audio begins, even before the call is answered. Useful for capturing pre-call audio, for example, IVR prompts. The default value is `false`.	No
channel	number	A number specifying which audio channel to transcribe in multichannel recordings. Each channel is a separate audio track—for example, `0` is left and `1` is `right` in stereo, or `0`, `1`, `2` for individual participants or microphones in multi-speaker recordings.	No

Additional vendor-specific options are available through properties like deepgramOptions, googleOptions, azureOptions, awsOptions, nuanceOptions, ibmOptions, nvidiaOptions, cobaltOptions, verbioOptions, speechmaticsOptions, assemblyAiOptions, openaiOptions, and customOptions.

More Information

Dial
Listen