• Supported service: stt
  • Key: deepgram
  • Integrated: Yes

​
Service options

Daily Bots supports Deepgram’s Live Audio API. You can configure any of Deepgram’s Live Audio body parameters as a service_option.

The default Deepgram configuration is:

- encoding="linear16",
- language=Language.EN,
- model="nova-2-general",
- sample_rate=16000,
- channels=1,
- interim_results=True,
- smart_format=True,
- punctuate=True,
- profanity_filter=True,
- vad_events=False,

Daily Bots has been tuned for ultra-low latency and this includes the configuration of Deepgram. For example, you’ll notice Deepgram’s VAD is disabled in favor of Daily’s VAD. We strongly recommend keeping this configuration in place.

model
string
default: "nova-2-general"

The model you want your STT service to use. Learn more.

{
  "service_options": {
    "deepgram": {
      "model": "nova-2-medical"
    }
  }
}
language
string
default: "en"

The language you want your STT service to use. Select any language from the available Deepgram STT languages.

{
  "service_options": {
    "deepgram": {
      "language": "es"
    }
  }
}
dictation
bool
default: "false"

Dictation automatically formats spoken commands for punctuation into their respective punctuation marks. Learn more.

{
  "service_options": {
    "deepgram": {
      "dictation": "false"
    }
  }
}
filler_words
bool
default: "false"

Indicates whether to include filler words like “uh” and “um” in transcript output. When set to true, these words will be included. Learn more.

{
  "service_options": {
    "deepgram": {
      "filler_word": "false"
    }
  }
}
keywords
string

Unique proper nouns or specialized terms you want the model to include in its predictions, which aren’t part of the model’s default vocabulary. Learn more.

{
  "service_options": {
    "deepgram": {
      "keywords": "snuffleupagus:5"
    }
  }
}
numerals
bool
default: "false"

Indicates whether to convert numbers from written format (e.g., one) to numerical format (e.g., 1). Learn more.

{
  "service_options": {
    "deepgram": {
      "numerals": "false"
    }
  }
}
profanity_filter
bool
default: "true"

Indicates whether to remove profanity from the transcript. Learn more.

{
  "service_options": {
    "deepgram": {
      "profanity_filter": "true"
    }
  }
}
punctuate
bool
default: "true"

Indicates whether to add punctuation and capitalization to the transcript. Learn more.

{
  "service_options": {
    "deepgram": {
      "punctuate": "true"
    }
  }
}
redact
string

Indicates whether to redact sensitive information, replacing redacted content with asterisks *. Learn more.

{
  "service_options": {
    "deepgram": {
      "redact": "ssn"
    }
  }
}
replace
string

Terms or phrases to search for in the submitted audio and replace. Learn more.

{
  "service_options": {
    "deepgram": {
      "replace": "monika:Monica"
    }
  }
}

​
Configuration options

model
string
default: "nova-2-general"

The model you want your STT service to use. Learn more.

{
  "name": "model",
  "value": "nova-2-general"
}
language
string
default: "en"

The language you want your STT service to use. Select any language from the available Deepgram STT languages.

{
  "name": "model",
  "value": "nova-2-general"
},
{
  "name": "language",
  "value": "es"
}
AssemblyAIGladia