v3

OpenAPI 3.1.02026-08-0321138121.5 KB
Pre-recorded V2

Initiate a new pre recorded job

post/v2/pre-recorded

Request body

custom_vocabularyboolean

[Beta] Can be either boolean to enable custom_vocabulary for this audio or an array with specific vocabulary list to feed the transcription model with

callback_urlstring uri

[Deprecated] Use callback/callback_config instead. Callback URL we will do a POST request to with the result of the transcription

callbackboolean

Enable callback for this transcription. If true, the callback_config property will be used to customize the callback behaviour

subtitlesboolean

Enable subtitles generation for this transcription

diarizationboolean

Enable speaker recognition (diarization) for this audio

translationboolean

[Beta] Enable translation for this audio

summarizationboolean

Enable summarization for this audio

named_entity_recognitionboolean

[Alpha] Enable named entity recognition for this audio

custom_spellingboolean

[Alpha] Enable custom spelling for this audio

sentiment_analysisboolean

Enable sentiment analysis for this audio

audio_to_llmboolean

Enable audio to LLM processing for this audio

pii_redactionboolean

Enable PII redaction for this audio

custom_metadataobject

Custom metadata you can attach to this transcription

sentencesboolean

Enable sentences for this audio

punctuation_enhancedboolean

[Alpha] Use enhanced punctuation for this audio

audio_urlstring uri required

URL to a Gladia file or to an external audio or video file

Example request

{
  "custom_vocabulary_config": {
    "vocabulary": [
      "Westeros",
      {
        "value": "Stark"
      },
      {
        "value": "Night's Watch",
        "pronunciations": [
          "Nightz Watch"
        ],
        "intensity": 0.4,
        "language": "en"
      }
    ],
    "default_intensity": 0.5
  },
  "callback_url": "https://callback.example",
  "callback_config": {
    "url": "https://callback.example"
  },
  "subtitles_config": {
    "formats": [
      "srt"
    ]
  },
  "diarization_config": {
    "number_of_speakers": 3,
    "min_speakers": 1,
    "max_speakers": 2
  },
  "translation_config": {
    "target_languages": [
      "en"
    ]
  },
  "custom_spelling_config": {
    "spelling_dictionary": {
      "Gettleman": [
        "gettleman"
      ],
      "SQL": [
        "Sequel"
      ]
    }
  },
  "audio_to_llm_config": {
    "prompts": [
      "Extract the key points from the transcription"
    ]
  },
  "pii_redaction_config": {
    "processed_text_type": "MARKER"
  },
  "custom_metadata": {
    "user": "John Doe"
  },
  "audio_url": "https://files.gladia.io/example/audio-transcription/split_infinity.wav"
}

Response

The pre recorded job has been initiated

idstring uuid required

Id of the job

result_urlstring uri required

Prebuilt URL with your transcription id to fetch the result

Example response

{
  "id": "45463597-20b7-4af7-b3b3-f5fb778203ab",
  "result_url": "https://api.gladia.io/v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab"
}