DeepgramTranscriptionOptions
Deepgram-specific transcription options passed as query parameters on the WebSocket connection URL.
Defined in: src/providers/stt/deepgram/DeepgramSTT.ts:29
Deepgram-specific transcription options passed as query parameters on the WebSocket connection URL.
Remarks
These options map to Deepgram’s real-time streaming API query parameters. They are set on the DeepgramSTTConfig.options property and appended to the WebSocket URL when the connection is established.
See
DeepgramSTTConfig for the full provider configuration
Properties
| Property | Type | Default value | Description | Defined in |
|---|---|---|---|---|
alternatives? | number | undefined | Number of transcription alternatives to return (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:104 |
channels? | number | undefined | Number of audio channels. | src/providers/stt/deepgram/DeepgramSTT.ts:56 |
detectEntities? | boolean | undefined | Extract named entities from the transcript (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:124 |
diarize? | boolean | undefined | Enable diarization / speaker detection (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:89 |
dictation? | boolean | undefined | Enable dictation mode (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:133 |
encoding? | string | undefined | Audio encoding format. Supported: 'linear16', 'linear32', 'flac', 'alaw', 'mulaw', 'amr-nb', 'amr-wb', 'opus', 'ogg-opus', 'speex', 'g729'. | src/providers/stt/deepgram/DeepgramSTT.ts:50 |
endpointing? | number | boolean | 10 | Automatic endpointing — milliseconds of silence before end-of-speech. Set to false to disable (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:118 |
extra? | string | string[] | undefined | Arbitrary key:value metadata passed through to the API (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:162 |
interimResults? | boolean | undefined | Enable interim results (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:110 |
keyterms? | string | string[] | undefined | Specialized terminology to boost recognition. Unlike keywords, keyterms use a more advanced boosting algorithm. Example ['CompositeVoice', 'WebSocket'] | src/providers/stt/deepgram/DeepgramSTT.ts:65 |
keywords? | string | string[] | undefined | Custom vocabulary or keywords to boost or suppress recognition (V1 only). Append a weight to boost/suppress: e.g. 'Deepgram:2' or 'erm:-10'. See keyterms for the newer boosting API (V1 & V2). | src/providers/stt/deepgram/DeepgramSTT.ts:101 |
language? | string | undefined | Language code (e.g., 'en-US', 'es'). | src/providers/stt/deepgram/DeepgramSTT.ts:42 |
mipOptOut? | boolean | undefined | Opt out of the Deepgram Model Improvement Program. | src/providers/stt/deepgram/DeepgramSTT.ts:71 |
model? | string | undefined | Nova model to use for V1 transcription. Available models: 'nova-3' (default), 'nova-3-medical', 'nova-2', 'nova-2-general', 'nova-2-meeting', 'nova-2-finance', 'nova-2-conversationalai', 'nova-2-voicemail', 'nova-2-video', 'nova-2-medical', 'nova-2-drivethru', 'nova-2-automotive', 'nova', 'enhanced', 'base'. | src/providers/stt/deepgram/DeepgramSTT.ts:39 |
multichannel? | boolean | undefined | Transcribe each audio channel independently (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:130 |
numerals? | boolean | undefined | Convert spoken numbers to digit form, e.g. “twenty one” → “21” (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:127 |
profanityFilter? | boolean | undefined | Enable profanity filter (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:79 |
punctuation? | boolean | undefined | Enable punctuation (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:76 |
redact? | string | string[] | undefined | Enable redaction of sensitive information (V1 only). Example ['pci', 'ssn', 'numbers'] | src/providers/stt/deepgram/DeepgramSTT.ts:86 |
replace? | string | string[] | undefined | Term replacement — swap recognized terms for preferred forms (V1 only). Example ['colour:color', 'grey:gray'] | src/providers/stt/deepgram/DeepgramSTT.ts:140 |
sampleRate? | number | undefined | Sample rate for audio data in Hz (required when encoding is set). | src/providers/stt/deepgram/DeepgramSTT.ts:53 |
search? | string | string[] | undefined | Search for specific terms or phrases in the transcript (V1 only). Example ['action item', 'follow up'] | src/providers/stt/deepgram/DeepgramSTT.ts:147 |
smartFormat? | boolean | undefined | Enable smart formatting — auto-punctuation and readability improvements (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:92 |
tag? | string | string[] | undefined | Labels for usage reporting in the Deepgram console. Multiple values are sent as separate tag= query parameters. | src/providers/stt/deepgram/DeepgramSTT.ts:68 |
utteranceEndMs? | number | undefined | Delay in milliseconds before emitting an UtteranceEnd event (V1 only). Controls the gap required between utterances. Example 1000 | src/providers/stt/deepgram/DeepgramSTT.ts:156 |
utterances? | boolean | undefined | Enable utterance segmentation (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:107 |
vadEvents? | boolean | undefined | Emit Voice Activity Detection events (SpeechStarted) (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:121 |
version? | string | undefined | Model version override (V1 only). | src/providers/stt/deepgram/DeepgramSTT.ts:159 |