> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gladia.io/llms.txt
> Use this file to discover all available pages before exploring further.
# List transcriptions
> (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/list).
List all the transcriptions matching the parameters.
## OpenAPI
````yaml GET /v2/transcription
openapi: 3.1.0
info:
title: Gladia Control API
description: ''
version: '1.0'
contact: {}
servers:
- url: https://api.gladia.io/
description: Gladia API production URL
security: []
tags: []
paths:
/v2/transcription:
get:
tags:
- Transcription V2
summary: Get transcription jobs based on query parameters
operationId: TranscriptionController_list_v2
parameters:
- name: offset
required: false
in: query
description: >-
The starting point for pagination. A value of 0 starts from the
first item.
schema:
minimum: 0
default: 0
type: integer
- name: limit
required: false
in: query
description: >-
The maximum number of items to return. Useful for pagination and
controlling data payload size.
schema:
minimum: 1
default: 20
type: integer
- name: date
required: false
in: query
description: Filter items relevant to a specific date in ISO format (YYYY-MM-DD).
schema:
format: date-time
example: '2026-05-05'
type: string
- name: before_date
required: false
in: query
description: Include items that occurred before the specified date in ISO format.
schema:
format: date-time
example: '2026-05-05T21:00:31.213Z'
type: string
- name: after_date
required: false
in: query
description: >-
Filter for items after the specified date. Use with `before_date`
for a range. Date in ISO format.
schema:
format: date-time
example: '2026-05-05T21:00:31.213Z'
type: string
- name: status
required: false
in: query
description: >-
Filter the list based on item status. Accepts multiple values from
the predefined list.
schema:
example:
- done
type: array
items:
type: string
enum:
- queued
- processing
- done
- error
- name: custom_metadata
required: false
in: query
schema:
additionalProperties: true
example:
user: John Doe
type: object
- name: kind
required: false
in: query
description: >-
Filter the list based on the item type. Supports multiple values
from the predefined list.
schema:
example:
- pre-recorded
type: array
items:
type: string
enum:
- pre-recorded
- live
responses:
'200':
description: A list of transcription jobs matching the parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/ListTranscriptionResponse'
'401':
description: You don't have the permissions to access transcription jobs
content:
application/json:
schema:
$ref: '#/components/schemas/UnauthorizedErrorResponse'
security:
- x_gladia_key: []
components:
schemas:
ListTranscriptionResponse:
type: object
properties:
first:
type: string
description: URL to fetch the first page
format: uri
example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
current:
type: string
description: URL to fetch the current page
format: uri
example: https://api.gladia.io/v2/transcription?status=done&offset=0&limit=20
next:
type: string
description: URL to fetch the next page
format: uri
example: >-
https://api.gladia.io/v2/transcription?status=done&offset=20&limit=20
nullable: true
items:
description: List of transcriptions
discriminator:
propertyName: kind
mapping:
pre-recorded:
$ref: '#/components/schemas/PreRecordedResponse'
live:
$ref: '#/components/schemas/StreamingResponse'
type: array
items:
oneOf:
- $ref: '#/components/schemas/PreRecordedResponse'
- $ref: '#/components/schemas/StreamingResponse'
required:
- first
- current
- next
- items
UnauthorizedErrorResponse:
type: object
properties:
timestamp:
type: string
description: Date of when the error occurred
example: '2023-12-28T09:04:17.210Z'
path:
type: string
description: Path to the API endpoint
example: /v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab
request_id:
type: string
description: Debug id
example: G-821fe9df
statusCode:
type: number
description: HTTP status code of the error
example: 401
message:
type: string
description: Error message
example: gladia key not found
required:
- timestamp
- path
- request_id
- statusCode
- message
PreRecordedResponse:
type: object
properties:
id:
type: string
description: Id of the job
format: uuid
example: 45463597-20b7-4af7-b3b3-f5fb778203ab
request_id:
type: string
description: Debug id
example: G-45463597
version:
type: integer
description: API version
example: 2
status:
type: string
description: >-
"queued": the job has been queued. "processing": the job is being
processed. "done": the job has been processed and the result is
available. "error": an error occurred during the job's processing.
enum:
- queued
- processing
- done
- error
created_at:
type: string
description: Creation date
format: date-time
example: '2023-12-28T09:04:17.210Z'
completed_at:
type: string
description: Completion date when status is "done" or "error"
format: date-time
example: '2023-12-28T09:04:37.210Z'
nullable: true
custom_metadata:
type: object
description: Custom metadata given in the initial request
example:
user: John Doe
additionalProperties: true
error_code:
type: integer
description: HTTP status code of the error if status is "error"
minimum: 400
maximum: 599
example: 500
nullable: true
post_session_metadata:
type: object
description: For debugging purposes, send data that could help to identify issues
kind:
type: string
enum:
- pre-recorded
example: pre-recorded
default: pre-recorded
file:
description: The file data you uploaded. Can be null if status is "error"
nullable: true
allOf:
- $ref: '#/components/schemas/FileResponse'
request_params:
description: >-
Parameters used for this pre-recorded transcription. Can be null if
status is "error"
nullable: true
allOf:
- $ref: '#/components/schemas/PreRecordedRequestParamsResponse'
result:
description: Pre-recorded transcription's result when status is "done"
nullable: true
allOf:
- $ref: '#/components/schemas/TranscriptionResultDTO'
required:
- id
- request_id
- version
- status
- created_at
- post_session_metadata
- kind
StreamingResponse:
type: object
properties:
id:
type: string
description: Id of the job
format: uuid
example: 45463597-20b7-4af7-b3b3-f5fb778203ab
request_id:
type: string
description: Debug id
example: G-45463597
version:
type: integer
description: API version
example: 2
status:
type: string
description: >-
"queued": the job has been queued. "processing": the job is being
processed. "done": the job has been processed and the result is
available. "error": an error occurred during the job's processing.
enum:
- queued
- processing
- done
- error
created_at:
type: string
description: Creation date
format: date-time
example: '2023-12-28T09:04:17.210Z'
completed_at:
type: string
description: Completion date when status is "done" or "error"
format: date-time
example: '2023-12-28T09:04:37.210Z'
nullable: true
custom_metadata:
type: object
description: Custom metadata given in the initial request
example:
user: John Doe
additionalProperties: true
error_code:
type: integer
description: HTTP status code of the error if status is "error"
minimum: 400
maximum: 599
example: 500
nullable: true
post_session_metadata:
type: object
description: For debugging purposes, send data that could help to identify issues
kind:
type: string
enum:
- live
example: live
default: live
file:
description: The file data you uploaded. Can be null if status is "error"
nullable: true
allOf:
- $ref: '#/components/schemas/FileResponse'
request_params:
description: >-
Parameters used for this live transcription. Can be null if status
is "error"
nullable: true
allOf:
- $ref: '#/components/schemas/StreamingRequestParamsResponse'
result:
description: Live transcription's result when status is "done"
nullable: true
allOf:
- $ref: '#/components/schemas/StreamingTranscriptionResultWithMessagesDTO'
required:
- id
- request_id
- version
- status
- created_at
- post_session_metadata
- kind
FileResponse:
type: object
properties:
id:
type: string
description: The file id
filename:
type: string
nullable: true
description: The name of the uploaded file
source:
type: string
nullable: true
description: The link used to download the file if audio_url was used
audio_duration:
type: number
nullable: true
description: Duration of the audio file
example: 3600
number_of_channels:
type: integer
nullable: true
description: Number of channels in the audio file
minimum: 1
example: 1
required:
- id
- filename
- source
- audio_duration
- number_of_channels
PreRecordedRequestParamsResponse:
type: object
properties:
custom_vocabulary:
type: boolean
description: >-
**[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
default: false
custom_vocabulary_config:
description: >-
**[Beta]** Custom vocabulary configuration, if `custom_vocabulary`
is enabled
allOf:
- $ref: '#/components/schemas/CustomVocabularyConfigDTO'
callback_url:
type: string
description: >-
**[Deprecated]** Use `callback`/`callback_config` instead. Callback
URL we will do a `POST` request to with the result of the
transcription
example: http://callback.example
format: uri
deprecated: true
callback:
type: boolean
description: >-
Enable callback for this transcription. If true, the
`callback_config` property will be used to customize the callback
behaviour
default: false
callback_config:
description: Customize the callback behaviour (url and http method)
allOf:
- $ref: '#/components/schemas/CallbackConfigDto'
subtitles:
type: boolean
description: Enable subtitles generation for this transcription
default: false
subtitles_config:
description: Configuration for subtitles generation if `subtitles` is enabled
allOf:
- $ref: '#/components/schemas/SubtitlesConfigDTO'
diarization:
type: boolean
description: Enable speaker recognition (diarization) for this audio
default: false
diarization_config:
description: Speaker recognition configuration, if `diarization` is enabled
allOf:
- $ref: '#/components/schemas/DiarizationConfigDTO'
translation:
type: boolean
description: '**[Beta]** Enable translation for this audio'
default: false
translation_config:
description: '**[Beta]** Translation configuration, if `translation` is enabled'
allOf:
- $ref: '#/components/schemas/TranslationConfigDTO'
summarization:
type: boolean
description: Enable summarization for this audio
default: false
summarization_config:
description: Summarization configuration, if `summarization` is enabled
allOf:
- $ref: '#/components/schemas/SummarizationConfigDTO'
named_entity_recognition:
type: boolean
description: '**[Alpha]** Enable named entity recognition for this audio'
default: false
custom_spelling:
type: boolean
description: '**[Alpha]** Enable custom spelling for this audio'
default: false
custom_spelling_config:
description: >-
**[Alpha]** Custom spelling configuration, if `custom_spelling` is
enabled
allOf:
- $ref: '#/components/schemas/CustomSpellingConfigDTO'
sentiment_analysis:
type: boolean
description: Enable sentiment analysis for this audio
default: false
audio_to_llm:
type: boolean
description: Enable audio to LLM processing for this audio
default: false
audio_to_llm_config:
description: Audio to LLM configuration, if `audio_to_llm` is enabled
allOf:
- $ref: '#/components/schemas/AudioToLlmListConfigDTO'
pii_redaction:
type: boolean
description: Enable PII redaction for this audio
default: false
pii_redaction_config:
description: PII redaction configuration, if `pii_redaction` is enabled
allOf:
- $ref: '#/components/schemas/PiiRedactionConfigDTO'
sentences:
type: boolean
description: Enable sentences for this audio
default: false
punctuation_enhanced:
type: boolean
description: '**[Alpha]** Use enhanced punctuation for this audio'
default: false
language_config:
description: Specify the language configuration
allOf:
- $ref: '#/components/schemas/LanguageConfig'
audio_url:
type: string
format: uri
nullable: true
required:
- audio_url
TranscriptionResultDTO:
type: object
properties:
metadata:
description: Metadata for the given transcription & audio file
allOf:
- $ref: '#/components/schemas/TranscriptionMetadataDTO'
transcription:
description: Transcription of the audio speech
allOf:
- $ref: '#/components/schemas/TranscriptionDTO'
translation:
description: >-
If `translation` has been enabled, translation of the audio speech
transcription
allOf:
- $ref: '#/components/schemas/TranslationDTO'
summarization:
description: >-
If `summarization` has been enabled, summarization of the audio
speech transcription
allOf:
- $ref: '#/components/schemas/SummarizationDTO'
moderation:
description: >-
If `moderation` has been enabled, moderation of the audio speech
transcription
allOf:
- $ref: '#/components/schemas/ModerationDTO'
named_entity_recognition:
description: >-
If `named_entity_recognition` has been enabled, the detected
entities
allOf:
- $ref: '#/components/schemas/NamedEntityRecognitionDTO'
name_consistency:
description: >-
If `name_consistency` has been enabled, Gladia will improve
consistency of the names accross the transcription
allOf:
- $ref: '#/components/schemas/NamesConsistencyDTO'
structured_data_extraction:
description: >-
If `structured_data_extraction` has been enabled, structured data
extraction results
allOf:
- $ref: '#/components/schemas/StructuredDataExtractionDTO'
sentiment_analysis:
description: >-
If `sentiment_analysis` has been enabled, sentiment analysis of the
audio speech transcription
allOf:
- $ref: '#/components/schemas/SentimentAnalysisDTO'
audio_to_llm:
description: >-
If `audio_to_llm` has been enabled, audio to llm results of the
audio speech transcription
allOf:
- $ref: '#/components/schemas/AudioToLlmListDTO'
sentences:
description: >-
If `sentences` has been enabled, sentences of the audio speech
transcription. Deprecated: content will move to the `transcription`
object.
deprecated: true
allOf:
- $ref: '#/components/schemas/SentencesDTO'
display_mode:
description: >-
If `display_mode` has been enabled, the output will be reordered,
creating new utterances when speakers overlapped
allOf:
- $ref: '#/components/schemas/DisplayModeDTO'
chapterization:
description: >-
If `chapterization` has been enabled, will generate chapters name
for different parts of the given audio.
allOf:
- $ref: '#/components/schemas/ChapterizationDTO'
diarization:
description: >-
If `diarization` has been requested and an error has occurred, the
result will appear here
allOf:
- $ref: '#/components/schemas/DiarizationDTO'
required:
- metadata
StreamingRequestParamsResponse:
type: object
properties:
encoding:
description: >-
The encoding format of the audio stream. Supported formats:
- PCM: 8, 16, 24, and 32 bits
- A-law: 8 bits
- μ-law: 8 bits
Note: No need to add WAV headers to raw audio as the API supports
both formats.
default: wav/pcm
allOf:
- $ref: '#/components/schemas/StreamingSupportedEncodingEnum'
bit_depth:
description: The bit depth of the audio stream
default: 16
allOf:
- $ref: '#/components/schemas/StreamingSupportedBitDepthEnum'
sample_rate:
description: The sample rate of the audio stream
default: 16000
allOf:
- $ref: '#/components/schemas/StreamingSupportedSampleRateEnum'
channels:
type: integer
description: The number of channels of the audio stream
default: 1
minimum: 1
maximum: 8
model:
description: The model used to process the audio. "solaria-1" is used by default.
default: solaria-1
allOf:
- $ref: '#/components/schemas/StreamingSupportedModels'
endpointing:
type: number
description: >-
The endpointing duration in seconds. Endpointing is the duration of
silence which will cause an utterance to be considered as finished
default: 0.05
minimum: 0.01
maximum: 10
maximum_duration_without_endpointing:
type: number
description: >-
The maximum duration in seconds without endpointing. If endpointing
is not detected after this duration, current utterance will be
considered as finished
default: 5
minimum: 5
maximum: 60
language_config:
description: Specify the language configuration
allOf:
- $ref: '#/components/schemas/LanguageConfig'
pre_processing:
description: Specify the pre-processing configuration
allOf:
- $ref: '#/components/schemas/PreProcessingConfig'
realtime_processing:
description: Specify the realtime processing configuration
allOf:
- $ref: '#/components/schemas/RealtimeProcessingConfig'
post_processing:
description: Specify the post-processing configuration
allOf:
- $ref: '#/components/schemas/PostProcessingConfig'
messages_config:
description: Specify the websocket messages configuration
allOf:
- $ref: '#/components/schemas/MessagesConfig'
callback:
type: boolean
description: If true, messages will be sent to configured url.
default: false
callback_config:
description: Specify the callback configuration
allOf:
- $ref: '#/components/schemas/CallbackConfig'
StreamingTranscriptionResultWithMessagesDTO:
type: object
properties:
metadata:
description: Metadata for the given transcription & audio file
allOf:
- $ref: '#/components/schemas/TranscriptionMetadataDTO'
transcription:
description: Transcription of the audio speech
allOf:
- $ref: '#/components/schemas/TranscriptionDTO'
translation:
description: >-
If `translation` has been enabled, translation of the audio speech
transcription
allOf:
- $ref: '#/components/schemas/TranslationDTO'
summarization:
description: >-
If `summarization` has been enabled, summarization of the audio
speech transcription
allOf:
- $ref: '#/components/schemas/SummarizationDTO'
named_entity_recognition:
description: >-
If `named_entity_recognition` has been enabled, the detected
entities
allOf:
- $ref: '#/components/schemas/NamedEntityRecognitionDTO'
sentiment_analysis:
description: >-
If `sentiment_analysis` has been enabled, sentiment analysis of the
audio speech transcription
allOf:
- $ref: '#/components/schemas/SentimentAnalysisDTO'
chapterization:
description: >-
If `chapterization` has been enabled, will generate chapters name
for different parts of the given audio.
allOf:
- $ref: '#/components/schemas/ChapterizationDTO'
messages:
description: Real-Time messages sent by the server during the live transcription
type: array
items:
type: string
required:
- metadata
CustomVocabularyConfigDTO:
type: object
properties:
vocabulary:
type: array
description: >-
Specific vocabulary list to feed the transcription model with. Each
item can be a string or an object with the following properties:
value, intensity, pronunciations, language.
example:
- Westeros
- value: Stark
- value: Night's Watch
pronunciations:
- Nightz Watch
intensity: 0.4
language: en
items:
oneOf:
- $ref: '#/components/schemas/CustomVocabularyEntryDTO'
- type: string
default_intensity:
type: number
description: Default intensity for the custom vocabulary
example: 0.5
minimum: 0
maximum: 1
required:
- vocabulary
CallbackConfigDto:
type: object
properties:
url:
type: string
description: The URL to be called with the result of the transcription
example: http://callback.example
format: uri
method:
description: >-
The HTTP method to be used. Allowed values are `POST` or `PUT`
(default: `POST`)
example: POST
default: POST
allOf:
- $ref: '#/components/schemas/CallbackMethodEnum'
required:
- url
SubtitlesConfigDTO:
type: object
properties:
formats:
type: array
description: Subtitles formats you want your transcription to be formatted to
default:
- srt
minItems: 1
example:
- srt
items:
$ref: '#/components/schemas/SubtitlesFormatEnum'
minimum_duration:
type: number
description: Minimum duration of a subtitle in seconds
minimum: 0
maximum_duration:
type: number
description: Maximum duration of a subtitle in seconds
minimum: 1
maximum: 30
maximum_characters_per_row:
type: integer
description: Maximum number of characters per row in a subtitle
minimum: 1
maximum_rows_per_caption:
type: integer
description: Maximum number of rows per caption
minimum: 1
maximum: 5
style:
description: >-
Style of the subtitles. Compliance mode refers to :
https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123
default: default
allOf:
- $ref: '#/components/schemas/SubtitlesStyleEnum'
DiarizationConfigDTO:
type: object
properties:
number_of_speakers:
type: integer
description: Exact number of speakers in the audio
example: 3
minimum: 1
min_speakers:
type: integer
description: Minimum number of speakers in the audio
example: 1
minimum: 0
max_speakers:
type: integer
description: Maximum number of speakers in the audio
example: 2
minimum: 0
TranslationConfigDTO:
type: object
properties:
target_languages:
type: array
description: >-
Target language in `iso639-1` format you want the transcription
translated to
example:
- en
minItems: 1
items:
$ref: '#/components/schemas/TranslationLanguageCodeEnum'
model:
description: Model you want the translation model to use to translate
default: base
allOf:
- $ref: '#/components/schemas/TranslationModelEnum'
match_original_utterances:
type: boolean
description: Align translated utterances with the original ones
default: true
lipsync:
type: boolean
description: 'Whether to apply lipsync to the translated transcription. '
default: true
context_adaptation:
type: boolean
description: >-
Enables or disables context-aware translation features that allow
the model to adapt translations based on provided context.
default: true
context:
type: string
description: Context information to improve translation accuracy
informal:
type: boolean
description: >-
Forces the translation to use informal language forms when available
in the target language.
default: false
required:
- target_languages
SummarizationConfigDTO:
type: object
properties:
type:
description: The type of summarization to apply
default: general
allOf:
- $ref: '#/components/schemas/SummaryTypesEnum'
CustomSpellingConfigDTO:
type: object
properties:
spelling_dictionary:
type: object
description: The list of spelling applied on the audio transcription
example:
Gettleman:
- gettleman
SQL:
- Sequel
additionalProperties:
type: array
items:
type: string
required:
- spelling_dictionary
AudioToLlmListConfigDTO:
type: object
properties:
prompts:
description: The list of prompts applied on the audio transcription
example:
- Extract the key points from the transcription
minItems: 1
type: array
items:
type: array
model:
type: string
description: >-
The model to use for the prompt execution. You can find the list of
supported models [here](https://openrouter.ai/models).
default: openai/gpt-5.4-nano
required:
- prompts
PiiRedactionConfigDTO:
type: object
properties:
entity_types:
description: The entity types to redact
example:
- GDPR
- HEALTH_INFORMATION
- HIPAA_SAFE_HARBOR
- QUEBEC_PRIVACY_ACT
- EMAIL_ADDRESS
- NAME
- PHONE_NUMBER
allOf:
- $ref: '#/components/schemas/PiiRedactionEntityTypeEnum'
processed_text_type:
type: string
description: The type of processed text to return (marker or mask)
enum:
- MARKER
- MASK
example: MARKER
LanguageConfig:
type: object
properties:
languages:
type: array
description: >-
If one language is set, it will be used for the transcription.
Otherwise, language will be auto-detected by the model.
default: []
items:
$ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
code_switching:
type: boolean
description: >-
If true, language will be auto-detected on each utterance.
Otherwise, language will be auto-detected on first utterance and
then used for the rest of the transcription. If one language is set,
this option will be ignored.
default: false
TranscriptionMetadataDTO:
type: object
properties:
audio_duration:
type: number
description: Duration of the transcribed audio file
example: 3600
number_of_distinct_channels:
type: integer
description: Number of distinct channels in the transcribed audio file
minimum: 1
example: 1
billing_time:
type: number
description: >-
Billed duration in seconds (audio_duration *
number_of_distinct_channels)
example: 3600
transcription_time:
type: number
description: Duration of the transcription in seconds
example: 20
required:
- audio_duration
- number_of_distinct_channels
- billing_time
- transcription_time
TranscriptionDTO:
type: object
properties:
full_transcript:
type: string
description: All transcription on text format without any other information
languages:
type: array
description: >-
All the detected languages in the audio sorted from the most
detected to the less detected
example:
- en
items:
$ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
sentences:
description: If `sentences` has been enabled, sentences results
type: array
items:
$ref: '#/components/schemas/SentencesDTO'
subtitles:
description: If `subtitles` has been enabled, subtitles results
type: array
items:
$ref: '#/components/schemas/SubtitleDTO'
utterances:
description: Transcribed speech utterances present in the audio
type: array
items:
$ref: '#/components/schemas/UtteranceDTO'
required:
- full_transcript
- languages
- utterances
TranslationDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: List of translated transcriptions, one for each `target_languages`
nullable: true
type: array
items:
$ref: '#/components/schemas/TranslationResultDTO'
required:
- success
- is_empty
- exec_time
- error
- results
SummarizationDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: string
description: If `summarization` has been enabled, summary of the transcription
nullable: true
required:
- success
- is_empty
- exec_time
- error
- results
ModerationDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: string
description: If `moderation` has been enabled, moderated transcription
nullable: true
required:
- success
- is_empty
- exec_time
- error
- results
NamedEntityRecognitionDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: >-
If `named_entity_recognition` has been enabled, the detected
entities.
nullable: true
type: array
items:
$ref: '#/components/schemas/NamedEntityRecognitionResult'
required:
- success
- is_empty
- exec_time
- error
- results
NamesConsistencyDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: string
description: >-
Deprecated, If `name_consistency` has been enabled, Gladia will
improve the consistency of the names across the transcription
required:
- success
- is_empty
- exec_time
- error
- results
StructuredDataExtractionDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: string
description: >-
If `structured_data_extraction` has been enabled, results of the AI
structured data extraction for the defined classes.
required:
- success
- is_empty
- exec_time
- error
- results
SentimentAnalysisDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: string
description: >-
If `sentiment_analysis` has been enabled, Gladia will analyze the
sentiments and emotions of the audio
required:
- success
- is_empty
- exec_time
- error
- results
AudioToLlmListDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: >-
If `audio_to_llm` has been enabled, results of the AI custom
analysis
nullable: true
type: array
items:
$ref: '#/components/schemas/AudioToLlmDTO'
required:
- success
- is_empty
- exec_time
- error
- results
SentencesDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: If `sentences` has been enabled, transcription as sentences.
nullable: true
type: array
items:
type: string
required:
- success
- is_empty
- exec_time
- error
- results
DisplayModeDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: >-
If `display_mode` has been enabled, proposes an alternative display
output.
nullable: true
type: array
items:
type: string
required:
- success
- is_empty
- exec_time
- error
- results
ChapterizationDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
type: object
description: >-
If `chapterization` has been enabled, will generate chapters name
for different parts of the given audio.
additionalProperties: true
required:
- success
- is_empty
- exec_time
- error
- results
DiarizationDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: >-
[Deprecated] If `diarization` has been enabled, the diarization
result will appear here
type: array
items:
$ref: '#/components/schemas/UtteranceDTO'
required:
- success
- is_empty
- exec_time
- error
- results
StreamingSupportedEncodingEnum:
type: string
enum:
- wav/pcm
- wav/alaw
- wav/ulaw
description: >-
The encoding format of the audio stream. Supported formats:
- PCM: 8, 16, 24, and 32 bits
- A-law: 8 bits
- μ-law: 8 bits
Note: No need to add WAV headers to raw audio as the API supports both
formats.
StreamingSupportedBitDepthEnum:
type: number
enum:
- 8
- 16
- 24
- 32
description: The bit depth of the audio stream
StreamingSupportedSampleRateEnum:
type: number
enum:
- 8000
- 16000
- 32000
- 44100
- 48000
description: The sample rate of the audio stream
StreamingSupportedModels:
type: string
enum:
- solaria-1
description: The model used to process the audio. "solaria-1" is used by default.
PreProcessingConfig:
type: object
properties:
audio_enhancer:
type: boolean
description: >-
If true, apply pre-processing to the audio stream to enhance the
quality.
default: false
speech_threshold:
type: number
description: >-
Sensitivity configuration for Speech Threshold. A value close to 1
will apply stricter thresholds, making it less likely to detect
background sounds as speech.
default: 0.6
minimum: 0
maximum: 1
RealtimeProcessingConfig:
type: object
properties:
custom_vocabulary:
type: boolean
description: If true, enable custom vocabulary for the transcription.
default: false
custom_vocabulary_config:
description: Custom vocabulary configuration, if `custom_vocabulary` is enabled
allOf:
- $ref: '#/components/schemas/CustomVocabularyConfigDTO'
custom_spelling:
type: boolean
description: If true, enable custom spelling for the transcription.
default: false
custom_spelling_config:
description: Custom spelling configuration, if `custom_spelling` is enabled
allOf:
- $ref: '#/components/schemas/CustomSpellingConfigDTO'
translation:
type: boolean
description: If true, enable translation for the transcription
default: false
translation_config:
description: Translation configuration, if `translation` is enabled
allOf:
- $ref: '#/components/schemas/TranslationConfigDTO'
named_entity_recognition:
type: boolean
description: If true, enable named entity recognition for the transcription.
default: false
sentiment_analysis:
type: boolean
description: If true, enable sentiment analysis for the transcription.
default: false
PostProcessingConfig:
type: object
properties:
summarization:
type: boolean
description: If true, generates summarization for the whole transcription.
default: false
summarization_config:
description: Summarization configuration, if `summarization` is enabled
allOf:
- $ref: '#/components/schemas/SummarizationConfigDTO'
chapterization:
type: boolean
description: If true, generates chapters for the whole transcription.
default: false
MessagesConfig:
type: object
properties:
receive_partial_transcripts:
type: boolean
description: If true, partial transcript will be sent to websocket.
default: false
receive_final_transcripts:
type: boolean
description: If true, final transcript will be sent to websocket.
default: true
receive_speech_events:
type: boolean
description: If true, begin and end speech events will be sent to websocket.
default: true
receive_pre_processing_events:
type: boolean
description: If true, pre-processing events will be sent to websocket.
default: true
receive_realtime_processing_events:
type: boolean
description: If true, realtime processing events will be sent to websocket.
default: true
receive_post_processing_events:
type: boolean
description: If true, post-processing events will be sent to websocket.
default: true
receive_acknowledgments:
type: boolean
description: If true, acknowledgments will be sent to websocket.
default: true
receive_errors:
type: boolean
description: If true, errors will be sent to websocket.
default: true
receive_lifecycle_events:
type: boolean
description: If true, lifecycle events will be sent to websocket.
default: false
CallbackConfig:
type: object
properties:
url:
type: string
description: URL on which we will do a `POST` request with configured messages
example: https://callback.example
format: uri
receive_partial_transcripts:
type: boolean
description: If true, partial transcript will be sent to the defined callback.
default: false
receive_final_transcripts:
type: boolean
description: If true, final transcript will be sent to the defined callback.
default: true
receive_speech_events:
type: boolean
description: >-
If true, begin and end speech events will be sent to the defined
callback.
default: false
receive_pre_processing_events:
type: boolean
description: If true, pre-processing events will be sent to the defined callback.
default: true
receive_realtime_processing_events:
type: boolean
description: >-
If true, realtime processing events will be sent to the defined
callback.
default: true
receive_post_processing_events:
type: boolean
description: >-
If true, post-processing events will be sent to the defined
callback.
default: true
receive_acknowledgments:
type: boolean
description: If true, acknowledgments will be sent to the defined callback.
default: false
receive_errors:
type: boolean
description: If true, errors will be sent to the defined callback.
default: false
receive_lifecycle_events:
type: boolean
description: If true, lifecycle events will be sent to the defined callback.
default: true
CustomVocabularyEntryDTO:
type: object
properties:
value:
type: string
description: The text used to replace in the transcription.
example: Gladia
intensity:
type: number
description: The global intensity of the feature.
example: 0.5
minimum: 0
maximum: 1
pronunciations:
description: The pronunciations used in the transcription.
type: array
items:
type: string
language:
description: >-
Specify the language in which it will be pronounced when sound
comparison occurs. Default to transcription language.
example: en
allOf:
- $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
required:
- value
CallbackMethodEnum:
type: string
enum:
- POST
- PUT
description: >-
The HTTP method to be used. Allowed values are `POST` or `PUT` (default:
`POST`)
SubtitlesFormatEnum:
type: string
enum:
- srt
- vtt
description: Subtitles formats you want your transcription to be formatted to
SubtitlesStyleEnum:
type: string
enum:
- default
- compliance
description: >-
Style of the subtitles. Compliance mode refers to :
https://loc.gov/preservation/digital/formats//fdd/fdd000569.shtml#:~:text=SRT%20files%20are%20basic%20text,alongside%2C%20example%3A%20%22MyVideo123
TranslationLanguageCodeEnum:
type: string
enum:
- af
- am
- ar
- as
- az
- ba
- be
- bg
- bn
- bo
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- es
- et
- eu
- fa
- fi
- fo
- fr
- gl
- gu
- ha
- haw
- he
- hi
- hr
- ht
- hu
- hy
- id
- is
- it
- ja
- jw
- ka
- kk
- km
- kn
- ko
- la
- lb
- ln
- lo
- lt
- lv
- mg
- mi
- mk
- ml
- mn
- mr
- ms
- mt
- my
- ne
- nl
- nn
- 'no'
- oc
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- sn
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- tg
- th
- tk
- tl
- tr
- tt
- uk
- ur
- uz
- vi
- wo
- yi
- yo
- zh
description: >-
Target language in `iso639-1` format you want the transcription
translated to
TranslationModelEnum:
type: string
enum:
- base
- enhanced
description: Model you want the translation model to use to translate
SummaryTypesEnum:
type: string
enum:
- general
- bullet_points
- concise
description: The type of summarization to apply
PiiRedactionEntityTypeEnum:
type: string
enum:
- APPI
- APPI_SENSITIVE
- CCI
- CORE_ENTITIES
- CPRA
- GDPR
- GDPR_SENSITIVE
- HEALTH_INFORMATION
- HIPAA_SAFE_HARBOR
- LIDI
- NUMERICAL_EXCL_PCI
- PCI
- QUEBEC_PRIVACY_ACT
- ACCOUNT_NUMBER
- AGE
- DATE
- DATE_INTERVAL
- DOB
- DRIVER_LICENSE
- DURATION
- EMAIL_ADDRESS
- EVENT
- FILENAME
- GENDER
- HEALTHCARE_NUMBER
- IP_ADDRESS
- LANGUAGE
- LOCATION
- LOCATION_ADDRESS
- LOCATION_ADDRESS_STREET
- LOCATION_CITY
- LOCATION_COORDINATE
- LOCATION_COUNTRY
- LOCATION_STATE
- LOCATION_ZIP
- MARITAL_STATUS
- MONEY
- NAME
- NAME_FAMILY
- NAME_GIVEN
- NAME_MEDICAL_PROFESSIONAL
- NUMERICAL_PII
- OCCUPATION
- ORGANIZATION
- ORGANIZATION_MEDICAL_FACILITY
- ORIGIN
- PASSPORT_NUMBER
- PASSWORD
- PHONE_NUMBER
- PHYSICAL_ATTRIBUTE
- POLITICAL_AFFILIATION
- RELIGION
- SEXUALITY
- SSN
- TIME
- URL
- USERNAME
- VEHICLE_ID
- ZODIAC_SIGN
- BLOOD_TYPE
- CONDITION
- DOSE
- DRUG
- INJURY
- MEDICAL_PROCESS
- STATISTICS
- BANK_ACCOUNT
- CREDIT_CARD
- CREDIT_CARD_EXPIRATION
- CVV
- ROUTING_NUMBER
- CORPORATE_ACTION
- DAY
- EFFECT
- FINANCIAL_METRIC
- MEDICAL_CODE
- MONTH
- ORGANIZATION_ID
- PRODUCT
- PROJECT
- TREND
- YEAR
description: The entity types to redact
TranscriptionLanguageCodeEnum:
type: string
enum:
- af
- am
- ar
- as
- az
- ba
- be
- bg
- bn
- bo
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- es
- et
- eu
- fa
- fi
- fo
- fr
- gl
- gu
- ha
- haw
- he
- hi
- hr
- ht
- hu
- hy
- id
- is
- it
- ja
- jw
- ka
- kk
- km
- kn
- ko
- la
- lb
- ln
- lo
- lt
- lv
- mg
- mi
- mk
- ml
- mn
- mr
- ms
- mt
- my
- ne
- nl
- nn
- 'no'
- oc
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- sn
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- tg
- th
- tk
- tl
- tr
- tt
- uk
- ur
- uz
- vi
- yi
- yo
- zh
description: >-
Specify the language in which it will be pronounced when sound
comparison occurs. Default to transcription language.
SubtitleDTO:
type: object
properties:
format:
description: Format of the current subtitle
example: srt
allOf:
- $ref: '#/components/schemas/SubtitlesFormatEnum'
subtitles:
type: string
description: Transcription on the asked subtitle format
required:
- format
- subtitles
UtteranceDTO:
type: object
properties:
start:
type: number
description: Start timestamp in seconds of this utterance
end:
type: number
description: End timestamp in seconds of this utterance
confidence:
type: number
description: Confidence on the transcribed utterance (1 = 100% confident)
channel:
type: integer
description: Audio channel of where this utterance has been transcribed from
minimum: 0
speaker:
type: integer
description: If `diarization` enabled, speaker identification number
minimum: 0
words:
description: List of words of the utterance, split by timestamp
type: array
items:
$ref: '#/components/schemas/WordDTO'
text:
type: string
description: Transcription for this utterance
language:
description: Spoken language in this utterance
example: en
allOf:
- $ref: '#/components/schemas/TranscriptionLanguageCodeEnum'
required:
- start
- end
- confidence
- channel
- words
- text
- language
AddonErrorDTO:
type: object
properties:
status_code:
type: integer
description: Status code of the addon error
example: 500
exception:
type: string
description: Reason of the addon error
message:
type: string
description: Detailed message of the addon error
required:
- status_code
- exception
- message
TranslationResultDTO:
type: object
properties:
error:
description: Contains the error details of the failed addon
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
full_transcript:
type: string
description: All transcription on text format without any other information
languages:
type: array
description: >-
All the detected languages in the audio sorted from the most
detected to the less detected
example:
- en
items:
$ref: '#/components/schemas/TranslationLanguageCodeEnum'
sentences:
description: >-
If `sentences` has been enabled, sentences results for this
translation
type: array
items:
$ref: '#/components/schemas/SentencesDTO'
subtitles:
description: >-
If `subtitles` has been enabled, subtitles results for this
translation
type: array
items:
$ref: '#/components/schemas/SubtitleDTO'
utterances:
description: Transcribed speech utterances present in the audio
type: array
items:
$ref: '#/components/schemas/UtteranceDTO'
required:
- error
- full_transcript
- languages
- utterances
NamedEntityRecognitionResult:
type: object
properties:
entity_type:
type: string
text:
type: string
start:
type: number
end:
type: number
required:
- entity_type
- text
- start
- end
AudioToLlmDTO:
type: object
properties:
success:
type: boolean
description: The audio intelligence model succeeded to get a valid output
is_empty:
type: boolean
description: The audio intelligence model returned an empty value
exec_time:
type: number
description: Time audio intelligence model took to complete the task
error:
description: >-
`null` if `success` is `true`. Contains the error details of the
failed model
nullable: true
allOf:
- $ref: '#/components/schemas/AddonErrorDTO'
results:
description: The result from a specific prompt
nullable: true
allOf:
- $ref: '#/components/schemas/AudioToLlmResultDTO'
required:
- success
- is_empty
- exec_time
- error
- results
WordDTO:
type: object
properties:
word:
type: string
description: Spoken word
start:
type: number
description: Start timestamps in seconds of the spoken word
end:
type: number
description: End timestamps in seconds of the spoken word
confidence:
type: number
description: Confidence on the transcribed word (1 = 100% confident)
required:
- word
- start
- end
- confidence
AudioToLlmResultDTO:
type: object
properties:
prompt:
type: string
description: The prompt used
nullable: true
response:
type: string
description: The result of the AI analysis
nullable: true
required:
- prompt
- response
securitySchemes:
x_gladia_key:
type: apiKey
in: header
name: x-gladia-key
description: Your personal Gladia API key
````