Initiate a transcription

Authorizations

x-gladia-key

string

header

required

Your personal Gladia API key

Body

application/json

audio_url

string<uri>

required

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

Example:

"http://files.gladia.io/example/audio-transcription/split_infinity.wav"

language_config

object

Specify the language configuration

Show child attributes

language_config.languages

enum<string>[]

If one language is set, it will be used for the transcription. Otherwise, language will be auto-detected by the model.

Available options:

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

language_config.code_switching

boolean

default:false

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.

custom_vocabulary

boolean

default:false

[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

custom_vocabulary_config

object

[Beta] Custom vocabulary configuration, if custom_vocabulary is enabled

Show child attributes

custom_vocabulary_config.vocabulary

(object | string)[]

required

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.

Show child attributes

custom_vocabulary_config.vocabulary.value

string

required

The text used to replace in the transcription.

Example:

"Gladia"

custom_vocabulary_config.vocabulary.intensity

number

The global intensity of the feature.

Required range: 0 <= x <= 1

Example:

0.5

custom_vocabulary_config.vocabulary.pronunciations

string[]

The pronunciations used in the transcription.

custom_vocabulary_config.vocabulary.language

enum<string>

Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription language.

Available options:

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

Example:

"en"

Example:

[
  "Westeros",
  { "value": "Stark" },
  {
    "value": "Night's Watch",
    "pronunciations": ["Nightz Watch"],
    "intensity": 0.4,
    "language": "en"
  }
]

custom_vocabulary_config.default_intensity

number

Default intensity for the custom vocabulary

Required range: 0 <= x <= 1

Example:

0.5

callback

boolean

default:false

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

callback_config

object

Customize the callback behaviour (url and http method)

Show child attributes

callback_config.url

string<uri>

required

The URL to be called with the result of the transcription

Example:

"http://callback.example"

callback_config.method

enum<string>

default:POST

The HTTP method to be used. Allowed values are POST or PUT (default: POST)

Available options:

POST,

PUT

Example:

"POST"

subtitles

boolean

default:false

Enable subtitles generation for this transcription

subtitles_config

object

Configuration for subtitles generation if subtitles is enabled

Show child attributes

subtitles_config.formats

enum<string>[]

Subtitles formats you want your transcription to be formatted to

Minimum array length: 1

Subtitles formats you want your transcription to be formatted to

Available options:

srt,

vtt

Example:

["srt"]

subtitles_config.minimum_duration

number

Minimum duration of a subtitle in seconds

Required range: x >= 0

subtitles_config.maximum_duration

number

Maximum duration of a subtitle in seconds

Required range: 1 <= x <= 30

subtitles_config.maximum_characters_per_row

integer

Maximum number of characters per row in a subtitle

Required range: x >= 1

subtitles_config.maximum_rows_per_caption

integer

Maximum number of rows per caption

Required range: 1 <= x <= 5

subtitles_config.style

enum<string>

default:default

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

Available options:

default,

compliance

diarization

boolean

default:false

Enable speaker recognition (diarization) for this audio

diarization_config

object

Speaker recognition configuration, if diarization is enabled

Show child attributes

diarization_config.number_of_speakers

integer

Exact number of speakers in the audio

Required range: x >= 1

Example:

3

diarization_config.min_speakers

integer

Minimum number of speakers in the audio

Required range: x >= 0

Example:

1

diarization_config.max_speakers

integer

Maximum number of speakers in the audio

Required range: x >= 0

Example:

2

translation

boolean

default:false

[Beta] Enable translation for this audio

translation_config

object

[Beta] Translation configuration, if translation is enabled

Show child attributes

translation_config.target_languages

enum<string>[]

required

Target language in iso639-1 format you want the transcription translated to

Minimum array length: 1

Target language in iso639-1 format you want the transcription translated to

Available options:

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

Example:

["en"]

translation_config.model

enum<string>

default:base

Model you want the translation model to use to translate

Available options:

base,

enhanced

translation_config.match_original_utterances

boolean

default:true

Align translated utterances with the original ones

translation_config.lipsync

boolean

default:true

Whether to apply lipsync to the translated transcription.

translation_config.context_adaptation

boolean

default:true

Enables or disables context-aware translation features that allow the model to adapt translations based on provided context.

translation_config.context

string

Context information to improve translation accuracy

translation_config.informal

boolean

default:false

Forces the translation to use informal language forms when available in the target language.

summarization

boolean

default:false

[Beta] Enable summarization for this audio

summarization_config

object

[Beta] Summarization configuration, if summarization is enabled

Show child attributes

summarization_config.type

enum<string>

default:general

The type of summarization to apply

Available options:

general,

bullet_points,

concise

named_entity_recognition

boolean

default:false

[Alpha] Enable named entity recognition for this audio

custom_spelling

boolean

default:false

[Alpha] Enable custom spelling for this audio

custom_spelling_config

object

[Alpha] Custom spelling configuration, if custom_spelling is enabled

Show child attributes

custom_spelling_config.spelling_dictionary

object

required

The list of spelling applied on the audio transcription

Show child attributes

custom_spelling_config.spelling_dictionary.{key}

string[]

Example:

{
  "Gettleman": ["gettleman"],
  "SQL": ["Sequel"]
}

sentiment_analysis

boolean

default:false

Enable sentiment analysis for this audio

audio_to_llm

boolean

default:false

[Alpha] Enable audio to llm processing for this audio

audio_to_llm_config

object

[Alpha] Audio to llm configuration, if audio_to_llm is enabled

Show child attributes

audio_to_llm_config.prompts

array[]

required

The list of prompts applied on the audio transcription

Minimum array length: 1

Example:

[
  "Extract the key points from the transcription"
]

custom_metadata

object

Custom metadata you can attach to this transcription

Example:

{ "user": "John Doe" }

sentences

boolean

default:false

Enable sentences for this audio

punctuation_enhanced

boolean

default:false

[Alpha] Use enhanced punctuation for this audio

Response

The pre recorded job has been initiated

string<uuid>

required

Id of the job

Example:

"45463597-20b7-4af7-b3b3-f5fb778203ab"

result_url

string<uri>

required

Prebuilt URL with your transcription id to fetch the result

Example:

"https://api.gladia.io/v2/transcription/45463597-20b7-4af7-b3b3-f5fb778203ab"

API Documentation

Live endpoints

Pre-recorded endpoints

Transcription (deprecated)

Initiate a transcription

Authorizations

Body

Response