NAiOS IconNAiOS Logo
Contacto
Volver al catálogo

Deepgram

deepgram

Deepgram provides AI-powered speech recognition and understanding services, offering APIs for real-time and pre-recorded audio transcription, text-to-speech, and audio intelligence.

Artificial IntelligenceTranscriptionWeb del proveedor
Acciones
9
Triggers
0
Autenticación
—
OAuth gestionado
No
Información técnica: el detalle de parámetros, schemas y triggers de esta página está pensado para equipos de integración. Si solo necesitas saber si tu herramienta favorita está disponible, basta con ver la lista de acciones.

Acciones disponibles (9)

Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.

Get Public ModelsDEEPGRAM_GET_MODELSAcción

Tool to retrieve metadata on all the latest public deepgram speech-to-text models. use when you need to list available models; set include outdated to true to include deprecated versions.

Parámetros de entrada

  • include_outdatedboolean

    If true, include all versions of every model; otherwise only the latest.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

List Deepgram ProjectsDEEPGRAM_GET_PROJECTSAcción

Tool to list all deepgram projects. use after authenticating with your api key.

Parámetros de entrada

Sin parámetros.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Get Project Usage SummaryDEEPGRAM_GET_PROJECT_USAGE_SUMMARYAcción

Tool to retrieve a summary of usage data for a specified deepgram project. use when you need high-level metrics (submitted, processed, billable durations, etc.) optionally filtered by time window, model, accessor, or tag.

Parámetros de entrada

  • endstring

    ISO 8601 end timestamp for the usage summary range

  • tagstring

    Filter results by tag

  • modelstring

    Filter results by model name

  • startstring

    ISO 8601 start timestamp for the usage summary range

  • project_idstringObligatorio

    Unique identifier of the Deepgram project

  • accessor_idstring

    Filter results by accessor ID

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Get Public TTS ModelsDEEPGRAM_GET_PUBLIC_TTS_MODELSAcción

Tool to fetch metadata about all latest public tts voice models. use when you need to list available deepgram tts voices.

Parámetros de entrada

  • include_outdatedboolean

    If true, include all versions of every model; otherwise only the latest.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

List Project ScopesDEEPGRAM_LIST_PROJECT_SCOPESAcción

Tool to list all scopes for a specified deepgram project. use when you need to retrieve all permission scopes for a project.

Parámetros de entrada

  • project_idstringObligatorio

    Unique identifier of the Deepgram project to list scopes for.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Transcribe Pre-recorded AudioDEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDEDAcción

Tool to transcribe pre-recorded audio files into text. use when you need to convert an audio file at a url to text after confirming the file url is publicly accessible.

Parámetros de entrada

  • tierstring

    Enhanced tier for higher-accuracy recognition.

  • modelstring

    Deepgram model to use (e.g., 'general', 'phonecall').

  • diarizeboolean

    Enable speaker diarization if true.

  • versionstring

    Specific model version to use.

  • keywordsstring[]

    List of keywords to spot in the transcript.

  • languagestring

    Language code for transcription (e.g., 'en-US').

  • audio_urlstringObligatoriouri

    Public URL of the audio file to transcribe.

  • punctuateboolean

    Automatically punctuate transcript.

  • alternativesinteger

    Number of alternative transcripts to return.

  • content_typestringObligatorioenum

    MIME type of the audio file.

    audio/wavaudio/mp3audio/mpegaudio/flacaudio/webm
  • smart_formatboolean

    Apply smart formatting (capitalization/punctuation).

  • detect_languageboolean

    Automatically detect language if true.

  • interim_resultsboolean

    Return interim results if true.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Summarize AudioDEEPGRAM_SUMMARIZE_AUDIOAcción

Tool to generate concise summaries from audio content. use when you need a quick summary of audio after confirming the file url is publicly accessible.

Parámetros de entrada

  • tierstring

    Set the accuracy tier for transcription.

  • modelstring

    Deepgram model to use for summarization (e.g., 'general').

  • languagestring

    Language code for the audio (e.g., 'en-US').

  • audio_urlstringObligatoriouri

    Public URL of the audio file to summarize.

  • punctuateboolean

    Automatically punctuate transcript.

  • content_typestringObligatorioenum

    MIME type of the audio file.

    audio/wavaudio/mp3audio/mpegaudio/flacaudio/webm
  • smart_formatboolean

    Apply smart formatting (capitalization and punctuation).

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Text-to-Speech (REST)DEEPGRAM_TEXT_TO_SPEECH_RESTAcción

Tool to convert text into natural-sounding speech. use when you need tts audio from text inputs.

Parámetros de entrada

  • textstringObligatorio

    The text to be synthesized into speech.

  • modelstring

    Deepgram TTS model to use (e.g., 'aura-asteria-en').

  • pitchnumber

    Pitch adjustment multiplier (0.5–2.0).

  • speednumber

    Speech rate multiplier (0.25–4.0).

  • voicestring

    Desired voice within the selected model.

  • versionstring

    Model version identifier.

  • encodingstring

    Audio encoding type (e.g., 'linear16', 'mp3').

  • languagestring

    Language code for synthesis (e.g., 'en-US').

  • containerstring

    Container format for audio (e.g., 'wav', 'mp3').

  • sample_rateinteger

    Desired sample rate for output audio in Hz (e.g., 16000).

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Topic DetectionDEEPGRAM_TOPIC_DETECTIONAcción

Tool to transcribe audio and detect topics. use when you need to identify the main topics discussed in an audio recording after confirming the file url is publicly accessible.

Parámetros de entrada

  • modelstring

    Deepgram model to use for transcription (e.g., 'general').

  • languagestring

    Language code for transcription (e.g., 'en-US').

  • audio_urlstringObligatoriouri

    Public URL of the audio file to analyze.

  • content_typestringObligatorioenum

    MIME type of the audio file.

    audio/wavaudio/mp3audio/mpegaudio/flacaudio/webm

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not