> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pinkfish.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# deepgram

> Speech-to-text and text-to-speech

**Server path:** `/deepgram` | **Type:** Application | **PCID required:** Yes

## Tools

| Tool                                                      | Description                                                                                                                                                                                                                |
| --------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`deepgram_transcribe_audio`](#deepgram_transcribe_audio) | Transcribe audio (or video) from a URL using Deepgram. Returns full Deepgram response including word-level timestamps in channels\[].alternatives\[].words\[]. Enable utterances/paragraphs/diarize for structured timing. |
| [`deepgram_transcribe_live`](#deepgram_transcribe_live)   | Start live audio transcription stream                                                                                                                                                                                      |
| [`deepgram_analyze_audio`](#deepgram_analyze_audio)       | Analyze audio for insights beyond transcription                                                                                                                                                                            |
| [`deepgram_get_usage`](#deepgram_get_usage)               | Get usage statistics for Deepgram API                                                                                                                                                                                      |
| [`deepgram_get_models`](#deepgram_get_models)             | Get available Deepgram models and languages                                                                                                                                                                                |
| [`deepgram_get_projects`](#deepgram_get_projects)         | Get list of Deepgram projects                                                                                                                                                                                              |

***

## deepgram\_transcribe\_audio

Transcribe audio (or video) from a URL using Deepgram. Returns full Deepgram response including word-level timestamps in channels\[].alternatives\[].words\[]. Enable utterances/paragraphs/diarize for structured timing.

**Parameters:**

| Parameter         | Type      | Required | Default    | Description                                                                                              |
| ----------------- | --------- | -------- | ---------- | -------------------------------------------------------------------------------------------------------- |
| `audioUrl`        | string    | Yes      | —          | URL of audio or video file to transcribe                                                                 |
| `model`           | string    | No       | `"nova-3"` | Deepgram model. Nova-3 is current best; required for keyterm.                                            |
| `language`        | string    | No       | `"en-US"`  | BCP-47 language code (e.g. en-US, es, fr)                                                                |
| `detectLanguage`  | boolean   | No       | —          | Auto-detect language instead of using `language`                                                         |
| `punctuate`       | boolean   | No       | `true`     | Add punctuation                                                                                          |
| `smartFormat`     | boolean   | No       | `true`     | Smart formatting: dates, times, numbers, etc. Recommended for most use cases.                            |
| `numerals`        | boolean   | No       | —          | Convert numbers to numerals (e.g. "one" → "1")                                                           |
| `profanityFilter` | boolean   | No       | —          | Filter profanity                                                                                         |
| `dictation`       | boolean   | No       | —          | Interpret spoken punctuation commands (e.g. "period", "comma")                                           |
| `measurements`    | boolean   | No       | —          | Normalize measurement abbreviations                                                                      |
| `fillerWords`     | boolean   | No       | —          | Include "um" / "uh" / etc. in transcript                                                                 |
| `diarize`         | boolean   | No       | —          | Enable speaker diarization                                                                               |
| `diarizeVersion`  | string    | No       | —          | Pin diarization algorithm version (e.g. "2023-09-15")                                                    |
| `utterances`      | boolean   | No       | —          | Group output into utterances with start/end timestamps. Often combined with diarize.                     |
| `uttSplit`        | number    | No       | —          | Silence threshold (seconds) for splitting utterances. Default 0.8.                                       |
| `paragraphs`      | boolean   | No       | —          | Group output into paragraphs with start/end timestamps.                                                  |
| `multichannel`    | boolean   | No       | —          | Transcribe each audio channel separately. Critical for stereo call recordings.                           |
| `alternatives`    | number    | No       | —          | Return N transcription candidates per channel with confidence                                            |
| `keywords`        | string\[] | No       | —          | Keyword boosting. Each entry may be "word" or "word:intensifier" (e.g. "Pinkfish:2"). Pre-Nova-3 models. |
| `keyterm`         | string\[] | No       | —          | Nova-3 keyterm boosting (superior to `keywords`). Multi-word phrases supported. English-only.            |
| `search`          | string\[] | No       | —          | Search for phrases; returns hits with timestamps                                                         |
| `replace`         | string\[] | No       | —          | Find-and-replace in transcript. Format: "find:replace" per entry.                                        |
| `summarize`       | string    | No       | —          | Generate summary. Pass true (v2) or "v2".                                                                |
| `detectTopics`    | boolean   | No       | —          | Detect topics                                                                                            |
| `customTopics`    | string\[] | No       | —          | Custom topics to detect (requires detectTopics)                                                          |
| `intents`         | boolean   | No       | —          | Detect intents                                                                                           |
| `customIntents`   | string\[] | No       | —          | Custom intents to detect (requires intents)                                                              |
| `sentiment`       | boolean   | No       | —          | Sentiment analysis per segment                                                                           |
| `redact`          | string\[] | No       | —          | Redaction options. Common: pci, pii, phi, numbers, ssn. Also supports specific entity types.             |
| `mipOptOut`       | boolean   | No       | —          | Opt out of Deepgram model improvement program (compliance)                                               |
| `tag`             | string\[] | No       | —          | Labels for Deepgram console analytics filtering                                                          |
| `extra`           | string\[] | No       | —          | Arbitrary key:value metadata passthrough. Format: "key:value" per entry.                                 |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "audioUrl": {
        "type": "string",
        "description": "URL of audio or video file to transcribe"
      },
      "model": {
        "type": "string",
        "enum": [
          "nova-3",
          "nova-3-general",
          "nova-3-medical",
          "nova-2",
          "nova-2-general",
          "nova-2-meeting",
          "nova-2-phonecall",
          "nova-2-voicemail",
          "nova-2-finance",
          "nova-2-conversationalai",
          "nova-2-video",
          "nova-2-medical",
          "nova-2-drivethru",
          "nova-2-automotive",
          "nova",
          "enhanced",
          "base",
          "whisper-tiny",
          "whisper-base",
          "whisper-small",
          "whisper-medium",
          "whisper-large"
        ],
        "default": "nova-3",
        "description": "Deepgram model. Nova-3 is current best; required for keyterm."
      },
      "language": {
        "type": "string",
        "default": "en-US",
        "description": "BCP-47 language code (e.g. en-US, es, fr)"
      },
      "detectLanguage": {
        "type": "boolean",
        "description": "Auto-detect language instead of using `language`"
      },
      "punctuate": {
        "type": "boolean",
        "default": true,
        "description": "Add punctuation"
      },
      "smartFormat": {
        "type": "boolean",
        "default": true,
        "description": "Smart formatting: dates, times, numbers, etc. Recommended for most use cases."
      },
      "numerals": {
        "type": "boolean",
        "description": "Convert numbers to numerals (e.g. \"one\" → \"1\")"
      },
      "profanityFilter": {
        "type": "boolean",
        "description": "Filter profanity"
      },
      "dictation": {
        "type": "boolean",
        "description": "Interpret spoken punctuation commands (e.g. \"period\", \"comma\")"
      },
      "measurements": {
        "type": "boolean",
        "description": "Normalize measurement abbreviations"
      },
      "fillerWords": {
        "type": "boolean",
        "description": "Include \"um\" / \"uh\" / etc. in transcript"
      },
      "diarize": {
        "type": "boolean",
        "description": "Enable speaker diarization"
      },
      "diarizeVersion": {
        "type": "string",
        "description": "Pin diarization algorithm version (e.g. \"2023-09-15\")"
      },
      "utterances": {
        "type": "boolean",
        "description": "Group output into utterances with start/end timestamps. Often combined with diarize."
      },
      "uttSplit": {
        "type": "number",
        "description": "Silence threshold (seconds) for splitting utterances. Default 0.8."
      },
      "paragraphs": {
        "type": "boolean",
        "description": "Group output into paragraphs with start/end timestamps."
      },
      "multichannel": {
        "type": "boolean",
        "description": "Transcribe each audio channel separately. Critical for stereo call recordings."
      },
      "alternatives": {
        "type": "number",
        "description": "Return N transcription candidates per channel with confidence"
      },
      "keywords": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Keyword boosting. Each entry may be \"word\" or \"word:intensifier\" (e.g. \"Pinkfish:2\"). Pre-Nova-3 models."
      },
      "keyterm": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Nova-3 keyterm boosting (superior to `keywords`). Multi-word phrases supported. English-only."
      },
      "search": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Search for phrases; returns hits with timestamps"
      },
      "replace": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Find-and-replace in transcript. Format: \"find:replace\" per entry."
      },
      "summarize": {
        "oneOf": [
          {
            "type": "boolean"
          },
          {
            "type": "string",
            "enum": [
              "v2"
            ]
          }
        ],
        "description": "Generate summary. Pass true (v2) or \"v2\"."
      },
      "detectTopics": {
        "type": "boolean",
        "description": "Detect topics"
      },
      "customTopics": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Custom topics to detect (requires detectTopics)"
      },
      "intents": {
        "type": "boolean",
        "description": "Detect intents"
      },
      "customIntents": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Custom intents to detect (requires intents)"
      },
      "sentiment": {
        "type": "boolean",
        "description": "Sentiment analysis per segment"
      },
      "redact": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "pci",
            "pii",
            "phi",
            "numbers",
            "ssn",
            "aggressive_numbers",
            "credit_card",
            "credit_card_expiration",
            "cvv",
            "email_address",
            "phone_number",
            "account_number",
            "age",
            "date",
            "date_interval",
            "dob",
            "driver_license",
            "healthcare_number",
            "ip_address",
            "location",
            "location_address",
            "location_zip",
            "location_coordinate",
            "money",
            "numerical_pii",
            "passport_number",
            "password",
            "time",
            "vehicle_id",
            "statistics",
            "bank_account",
            "routing_number"
          ]
        },
        "description": "Redaction options. Common: pci, pii, phi, numbers, ssn. Also supports specific entity types."
      },
      "mipOptOut": {
        "type": "boolean",
        "description": "Opt out of Deepgram model improvement program (compliance)"
      },
      "tag": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Labels for Deepgram console analytics filtering"
      },
      "extra": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Arbitrary key:value metadata passthrough. Format: \"key:value\" per entry."
      }
    },
    "required": [
      "PCID",
      "audioUrl"
    ]
  }
  ```
</Expandable>

***

## deepgram\_transcribe\_live

Start live audio transcription stream

**Parameters:**

| Parameter        | Type      | Required | Default    | Description                           |
| ---------------- | --------- | -------- | ---------- | ------------------------------------- |
| `model`          | string    | No       | `"nova-3"` | Deepgram model                        |
| `language`       | string    | No       | `"en-US"`  | Language code                         |
| `punctuate`      | boolean   | No       | `true`     | Add punctuation                       |
| `smartFormat`    | boolean   | No       | `true`     | Smart formatting                      |
| `numerals`       | boolean   | No       | —          | Convert numbers to numerals           |
| `fillerWords`    | boolean   | No       | —          | Include filler words                  |
| `diarize`        | boolean   | No       | —          | Enable speaker diarization            |
| `multichannel`   | boolean   | No       | —          | Per-channel transcription             |
| `keywords`       | string\[] | No       | —          | Keyword boosting                      |
| `keyterm`        | string\[] | No       | —          | Nova-3 keyterm boosting               |
| `interimResults` | boolean   | No       | `true`     | Return interim results                |
| `endpointing`    | number    | No       | —          | Endpointing sensitivity (0-500ms)     |
| `vadEvents`      | boolean   | No       | —          | Voice activity detection events       |
| `uttSplit`       | number    | No       | —          | Utterance split silence threshold (s) |
| `tag`            | string\[] | No       | —          | Analytics labels                      |
| `mipOptOut`      | boolean   | No       | —          | Opt out of model improvement          |
| `redact`         | string\[] | No       | —          | Redaction options (streaming subset)  |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "enum": [
          "nova-3",
          "nova-3-general",
          "nova-3-medical",
          "nova-2",
          "nova-2-general",
          "nova-2-meeting",
          "nova-2-phonecall",
          "nova-2-voicemail",
          "nova-2-finance",
          "nova-2-conversationalai",
          "nova-2-video",
          "nova-2-medical",
          "nova-2-drivethru",
          "nova-2-automotive",
          "nova",
          "enhanced",
          "base",
          "whisper-tiny",
          "whisper-base",
          "whisper-small",
          "whisper-medium",
          "whisper-large"
        ],
        "default": "nova-3",
        "description": "Deepgram model"
      },
      "language": {
        "type": "string",
        "default": "en-US",
        "description": "Language code"
      },
      "punctuate": {
        "type": "boolean",
        "default": true,
        "description": "Add punctuation"
      },
      "smartFormat": {
        "type": "boolean",
        "default": true,
        "description": "Smart formatting"
      },
      "numerals": {
        "type": "boolean",
        "description": "Convert numbers to numerals"
      },
      "fillerWords": {
        "type": "boolean",
        "description": "Include filler words"
      },
      "diarize": {
        "type": "boolean",
        "description": "Enable speaker diarization"
      },
      "multichannel": {
        "type": "boolean",
        "description": "Per-channel transcription"
      },
      "keywords": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Keyword boosting"
      },
      "keyterm": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Nova-3 keyterm boosting"
      },
      "interimResults": {
        "type": "boolean",
        "default": true,
        "description": "Return interim results"
      },
      "endpointing": {
        "type": "number",
        "description": "Endpointing sensitivity (0-500ms)"
      },
      "vadEvents": {
        "type": "boolean",
        "description": "Voice activity detection events"
      },
      "uttSplit": {
        "type": "number",
        "description": "Utterance split silence threshold (s)"
      },
      "tag": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Analytics labels"
      },
      "mipOptOut": {
        "type": "boolean",
        "description": "Opt out of model improvement"
      },
      "redact": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "pci",
            "phi",
            "numbers",
            "aggressive_numbers",
            "ssn"
          ]
        },
        "description": "Redaction options (streaming subset)"
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>

***

## deepgram\_analyze\_audio

Analyze audio for insights beyond transcription

**Parameters:**

| Parameter  | Type      | Required | Default   | Description                  |
| ---------- | --------- | -------- | --------- | ---------------------------- |
| `audioUrl` | string    | Yes      | —         | URL of audio file to analyze |
| `features` | string\[] | Yes      | —         | Analysis features to include |
| `language` | string    | No       | `"en-US"` | Language code                |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "audioUrl": {
        "type": "string",
        "description": "URL of audio file to analyze"
      },
      "features": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "sentiment",
            "topics",
            "intents",
            "summarize"
          ]
        },
        "description": "Analysis features to include"
      },
      "language": {
        "type": "string",
        "default": "en-US",
        "description": "Language code"
      }
    },
    "required": [
      "PCID",
      "audioUrl",
      "features"
    ]
  }
  ```
</Expandable>

***

## deepgram\_get\_usage

Get usage statistics for Deepgram API

**Parameters:**

| Parameter         | Type    | Required | Default | Description                          |
| ----------------- | ------- | -------- | ------- | ------------------------------------ |
| `startDate`       | string  | Yes      | —       | Start date (YYYY-MM-DD format)       |
| `endDate`         | string  | Yes      | —       | End date (YYYY-MM-DD format)         |
| `includeRequests` | boolean | No       | `false` | Include detailed request information |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "startDate": {
        "type": "string",
        "description": "Start date (YYYY-MM-DD format)"
      },
      "endDate": {
        "type": "string",
        "description": "End date (YYYY-MM-DD format)"
      },
      "includeRequests": {
        "type": "boolean",
        "default": false,
        "description": "Include detailed request information"
      }
    },
    "required": [
      "PCID",
      "startDate",
      "endDate"
    ]
  }
  ```
</Expandable>

***

## deepgram\_get\_models

Get available Deepgram models and languages

**Parameters:**

| Parameter         | Type    | Required | Default | Description             |
| ----------------- | ------- | -------- | ------- | ----------------------- |
| `includeOutdated` | boolean | No       | `false` | Include outdated models |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "includeOutdated": {
        "type": "boolean",
        "default": false,
        "description": "Include outdated models"
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>

***

## deepgram\_get\_projects

Get list of Deepgram projects

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>