Vulavula Transcription API

Endpointhttps://api.lelapa.ai

Transcribe an audio file (received as a file) in one request

POST

https://api.lelapa.ai

/v1/transcribe/sync

Transcribe an audio file (received as a file) in one request › query Parameters

lang_code

diarise

boolean

Enable diarisation

Default: false

detect_music

boolean

Enable music detection

Default: false

Transcribe an audio file (received as a file) in one request › Request Body

file

string · binary · required

Transcribe an audio file (received as a file) in one request › Responses

Successful Response

POST/v1/transcribe/sync

import requests

url = "https://api.lelapa.ai/v1/transcribe/sync"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nfile\r\n-----011000010111000001101001--"
headers = {"Content-Type": "multipart/form-data; boundary=---011000010111000001101001"}

response = requests.post(url, data=payload, headers=headers)

print(response.text)

python

Example Request Body

{
  "file": "file"
}

json

Example Responses

{
  "id": "string",
  "upload_file_size": 0,
  "audio_length_seconds": 0,
  "sample_rate": 0,
  "channels": 0,
  "frame_rate": 0,
  "mime_type": "string",
  "language_code": "string",
  "diarisation_result": {
    "timeline": [
      {
        "start_time": 0,
        "end_time": 0,
        "type": "type",
        "speaker_id": "string",
        "text": "string"
      }
    ],
    "words": [
      {
        "word": "word",
        "start_time": 0,
        "end_time": 0,
        "confidence": 0,
        "weight": 0,
        "word_intensity": 0,
        "best_path": 0,
        "speaker_id": "speaker_id"
      }
    ]
  },
  "transcription_text": "string",
  "transcription_status": "string",
  "error_message": "string",
  "status_datetime": "2024-08-25T15:00:00Z",
  "upload_datetime": "2024-08-25T15:00:00Z",
  "warnings": [
    "string"
  ]
}

json

application/json

List all the batches that have been created

GET

https://api.lelapa.ai

/v1/transcribe/batch

List all the batches that have been created › Responses

Successful Response

object[]

status

string · required

Keychain ID.

GET/v1/transcribe/batch

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch"

response = requests.get(url)

print(response.text)

python

Example Responses

[
  {
    "id": "string",
    "keychain_id": "00000000-0000-0000-0000-000000000000",
    "status": "status",
    "language_code": "string",
    "created_at": "2024-08-25T15:00:00Z",
    "updated_at": "2024-08-25T15:00:00Z"
  }
]

json

application/json

Request a container to upload files for bulk processing

POST

https://api.lelapa.ai

/v1/transcribe/batch

Request a container to upload files for bulk processing › Responses

Successful Response

batch_id

string · required

blob_endpoint

string · required

sas_token

string · required

POST/v1/transcribe/batch

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch"

response = requests.post(url)

print(response.text)

python

Example Responses

{
  "batch_id": "batch_id",
  "blob_endpoint": "blob_endpoint",
  "sas_token": "sas_token"
}

json

application/json

Kick off the transcription process for a batch of files

POST

https://api.lelapa.ai

/v1/transcribe/batch/{id}/process

Kick off the transcription process for a batch of files › path Parameters

id

string · required

Kick off the transcription process for a batch of files › query Parameters

lang_code

Language of audio if known. Choose: zul, sot, eng, afr, fra

diarise

boolean

Enable diarisation

Default: false

Kick off the transcription process for a batch of files › Responses

Successful Response

No data returned

POST/v1/transcribe/batch/{id}/process

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id/process"

response = requests.post(url)

print(response.text)

python

Example Responses

{}

json

application/json

Get more details of a specific batch

GET

https://api.lelapa.ai

/v1/transcribe/batch/{id}

Get more details of a specific batch › path Parameters

id

string · required

Get more details of a specific batch › Responses

Successful Response

status

string · required

Keychain ID.

GET/v1/transcribe/batch/{id}

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id"

response = requests.get(url)

print(response.text)

python

Example Responses

{
  "id": "string",
  "keychain_id": "00000000-0000-0000-0000-000000000000",
  "status": "status",
  "language_code": "string",
  "created_at": "2024-08-25T15:00:00Z",
  "updated_at": "2024-08-25T15:00:00Z"
}

json

application/json

List all the transcripts in a batch

GET

https://api.lelapa.ai

/v1/transcribe/batch/{id}/transcriptions

List all the transcripts in a batch › path Parameters

id

string · required

List all the transcripts in a batch › Responses

Successful Response

object[]

GET/v1/transcribe/batch/{id}/transcriptions

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id/transcriptions"

response = requests.get(url)

print(response.text)

python

Example Responses

[
  {
    "id": "string",
    "upload_file_size": 0,
    "audio_length_seconds": 0,
    "sample_rate": 0,
    "channels": 0,
    "frame_rate": 0,
    "mime_type": "string",
    "language_code": "string",
    "diarisation_result": {
      "timeline": [
        {
          "start_time": 0,
          "end_time": 0,
          "type": "type",
          "speaker_id": "string",
          "text": "string"
        }
      ],
      "words": [
        {
          "word": "word",
          "start_time": 0,
          "end_time": 0,
          "confidence": 0,
          "weight": 0,
          "word_intensity": 0,
          "best_path": 0,
          "speaker_id": "speaker_id"
        }
      ]
    },
    "transcription_text": "string",
    "transcription_status": "string",
    "error_message": "string",
    "status_datetime": "2024-08-25T15:00:00Z",
    "upload_datetime": "2024-08-25T15:00:00Z",
    "warnings": [
      "string"
    ]
  }
]

json

application/json

Get usage statistics for the customer

GET

https://api.lelapa.ai

/v1/transcribe/usage

GET TRANSCRIBE USAGE

Accepts a start date, end date, and interval and returns usage statistics for the customer.

Args

start_date_time: start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
end_date_time: end date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
interval: interval for aggregating data (e.g., 'minute', 'hour', 'day')

Returns

TranscribeUsageReport: a report containing usage statistics for the customer

Raises

HTTPException 400: if the date format is invalid | if the interval is invalid | if the start date is after the end date

Get usage statistics for the customer › query Parameters

start_date_time

string · required

Start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

end_date_time

string · required

End date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

interval

string · required

Interval for aggregating data (e.g., 'minute', 'hour', 'day')

Get usage statistics for the customer › Responses

Successful Response

total_invocations

integer · required

total_successful_invocations

integer · required

total_failed_invocations

integer · required

total_pending_invocations

integer · required

total_seconds_transcribed

number · required

total_tokens

integer · required

start_date_time

string · required

end_date_time

string · required

interval

string · required

object[]

Default: []

GET/v1/transcribe/usage

import requests

url = "https://api.lelapa.ai/v1/transcribe/usage?start_date_time=%3Cstring%3E&end_date_time=%3Cstring%3E&interval=%3Cstring%3E"

response = requests.get(url)

print(response.text)

python

Example Responses

{
  "usage": [
    {
      "period": "period",
      "invocations": 0,
      "successful_invocations": 0,
      "failed_invocations": 0,
      "pending_invocations": 0,
      "seconds_transcribed": 0,
      "tokens": 0
    }
  ],
  "total_invocations": 0,
  "total_successful_invocations": 0,
  "total_failed_invocations": 0,
  "total_pending_invocations": 0,
  "total_seconds_transcribed": 0,
  "total_tokens": 0,
  "start_date_time": "start_date_time",
  "end_date_time": "end_date_time",
  "interval": "interval"
}

json

application/json

Vulavula Transcription API

Endpointhttps://api.lelapa.ai

Transcribe an audio file (received as a file) in one request

POST

https://api.lelapa.ai

/v1/transcribe/sync

Transcribe an audio file (received as a file) in one request › query Parameters

lang_code

diarise

boolean

Enable diarisation

Default: false

detect_music

boolean

Enable music detection

Default: false

Transcribe an audio file (received as a file) in one request › Request Body

file

string · binary · required

Transcribe an audio file (received as a file) in one request › Responses

Successful Response

POST/v1/transcribe/sync

import requests

url = "https://api.lelapa.ai/v1/transcribe/sync"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nfile\r\n-----011000010111000001101001--"
headers = {"Content-Type": "multipart/form-data; boundary=---011000010111000001101001"}

response = requests.post(url, data=payload, headers=headers)

print(response.text)

python

Example Request Body

{
  "file": "file"
}

json

Example Responses

{
  "id": "string",
  "upload_file_size": 0,
  "audio_length_seconds": 0,
  "sample_rate": 0,
  "channels": 0,
  "frame_rate": 0,
  "mime_type": "string",
  "language_code": "string",
  "diarisation_result": {
    "timeline": [
      {
        "start_time": 0,
        "end_time": 0,
        "type": "type",
        "speaker_id": "string",
        "text": "string"
      }
    ],
    "words": [
      {
        "word": "word",
        "start_time": 0,
        "end_time": 0,
        "confidence": 0,
        "weight": 0,
        "word_intensity": 0,
        "best_path": 0,
        "speaker_id": "speaker_id"
      }
    ]
  },
  "transcription_text": "string",
  "transcription_status": "string",
  "error_message": "string",
  "status_datetime": "2024-08-25T15:00:00Z",
  "upload_datetime": "2024-08-25T15:00:00Z",
  "warnings": [
    "string"
  ]
}

json

application/json

List all the batches that have been created

GET

https://api.lelapa.ai

/v1/transcribe/batch

List all the batches that have been created › Responses

Successful Response

object[]

status

string · required

Keychain ID.

GET/v1/transcribe/batch

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch"

response = requests.get(url)

print(response.text)

python

Example Responses

[
  {
    "id": "string",
    "keychain_id": "00000000-0000-0000-0000-000000000000",
    "status": "status",
    "language_code": "string",
    "created_at": "2024-08-25T15:00:00Z",
    "updated_at": "2024-08-25T15:00:00Z"
  }
]

json

application/json

Request a container to upload files for bulk processing

POST

https://api.lelapa.ai

/v1/transcribe/batch

Request a container to upload files for bulk processing › Responses

Successful Response

batch_id

string · required

blob_endpoint

string · required

sas_token

string · required

POST/v1/transcribe/batch

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch"

response = requests.post(url)

print(response.text)

python

Example Responses

{
  "batch_id": "batch_id",
  "blob_endpoint": "blob_endpoint",
  "sas_token": "sas_token"
}

json

application/json

Kick off the transcription process for a batch of files

POST

https://api.lelapa.ai

/v1/transcribe/batch/{id}/process

Kick off the transcription process for a batch of files › path Parameters

id

string · required

Kick off the transcription process for a batch of files › query Parameters

lang_code

Language of audio if known. Choose: zul, sot, eng, afr, fra

diarise

boolean

Enable diarisation

Default: false

Kick off the transcription process for a batch of files › Responses

Successful Response

No data returned

POST/v1/transcribe/batch/{id}/process

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id/process"

response = requests.post(url)

print(response.text)

python

Example Responses

{}

json

application/json

Get more details of a specific batch

GET

https://api.lelapa.ai

/v1/transcribe/batch/{id}

Get more details of a specific batch › path Parameters

id

string · required

Get more details of a specific batch › Responses

Successful Response

status

string · required

Keychain ID.

GET/v1/transcribe/batch/{id}

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id"

response = requests.get(url)

print(response.text)

python

Example Responses

{
  "id": "string",
  "keychain_id": "00000000-0000-0000-0000-000000000000",
  "status": "status",
  "language_code": "string",
  "created_at": "2024-08-25T15:00:00Z",
  "updated_at": "2024-08-25T15:00:00Z"
}

json

application/json

List all the transcripts in a batch

GET

https://api.lelapa.ai

/v1/transcribe/batch/{id}/transcriptions

List all the transcripts in a batch › path Parameters

id

string · required

List all the transcripts in a batch › Responses

Successful Response

object[]

GET/v1/transcribe/batch/{id}/transcriptions

import requests

url = "https://api.lelapa.ai/v1/transcribe/batch/:id/transcriptions"

response = requests.get(url)

print(response.text)

python

Example Responses

[
  {
    "id": "string",
    "upload_file_size": 0,
    "audio_length_seconds": 0,
    "sample_rate": 0,
    "channels": 0,
    "frame_rate": 0,
    "mime_type": "string",
    "language_code": "string",
    "diarisation_result": {
      "timeline": [
        {
          "start_time": 0,
          "end_time": 0,
          "type": "type",
          "speaker_id": "string",
          "text": "string"
        }
      ],
      "words": [
        {
          "word": "word",
          "start_time": 0,
          "end_time": 0,
          "confidence": 0,
          "weight": 0,
          "word_intensity": 0,
          "best_path": 0,
          "speaker_id": "speaker_id"
        }
      ]
    },
    "transcription_text": "string",
    "transcription_status": "string",
    "error_message": "string",
    "status_datetime": "2024-08-25T15:00:00Z",
    "upload_datetime": "2024-08-25T15:00:00Z",
    "warnings": [
      "string"
    ]
  }
]

json

application/json

Get usage statistics for the customer

GET

https://api.lelapa.ai

/v1/transcribe/usage

GET TRANSCRIBE USAGE

Accepts a start date, end date, and interval and returns usage statistics for the customer.

Args

start_date_time: start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
end_date_time: end date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
interval: interval for aggregating data (e.g., 'minute', 'hour', 'day')

Returns

TranscribeUsageReport: a report containing usage statistics for the customer

Raises

HTTPException 400: if the date format is invalid | if the interval is invalid | if the start date is after the end date

Get usage statistics for the customer › query Parameters

start_date_time

string · required

Start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

end_date_time

string · required

End date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

interval

string · required

Interval for aggregating data (e.g., 'minute', 'hour', 'day')

Get usage statistics for the customer › Responses

Successful Response

total_invocations

integer · required

total_successful_invocations

integer · required

total_failed_invocations

integer · required

total_pending_invocations

integer · required

total_seconds_transcribed

number · required

total_tokens

integer · required

start_date_time

string · required

end_date_time

string · required

interval

string · required

object[]

Default: []

GET/v1/transcribe/usage

import requests

url = "https://api.lelapa.ai/v1/transcribe/usage?start_date_time=%3Cstring%3E&end_date_time=%3Cstring%3E&interval=%3Cstring%3E"

response = requests.get(url)

print(response.text)

python

Example Responses

{
  "usage": [
    {
      "period": "period",
      "invocations": 0,
      "successful_invocations": 0,
      "failed_invocations": 0,
      "pending_invocations": 0,
      "seconds_transcribed": 0,
      "tokens": 0
    }
  ],
  "total_invocations": 0,
  "total_successful_invocations": 0,
  "total_failed_invocations": 0,
  "total_pending_invocations": 0,
  "total_seconds_transcribed": 0,
  "total_tokens": 0,
  "start_date_time": "start_date_time",
  "end_date_time": "end_date_time",
  "interval": "interval"
}

json

application/json