Bhashik Speech API

Text to Speech

post

Convert input text to an audio file in the specified language and speaker voice.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

input_textstringRequired

Input text to synthesize.

input_languagestring · enumRequired

Language code

Possible values:

input_speakerstring · enumRequiredPossible values:

Responses

200

Audio file link

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/tts

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/tts HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 202

{
  "input_text": "Major exports include petroleum products, textile goods, jewellery, software, engineering goods, chemicals, and manufactured leather goods.",
  "input_language": "eng",
  "input_speaker": "male"
}

{
  "status": "success",
  "data": {
    "audio_file": "https://.../audio-12345.wav"
  }
}

Text to Speech Translation

post

Translate input text from source language to target language and return synthesized speech.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

application/json

input_textstringRequired

Input text to translate and synthesize.

src_lang_codestring · enumRequired

Only 'eng' is supported as the source for certain translation endpoints.

Possible values:

tgt_lang_codestring · enumRequired

Target language code

Possible values:

input_speakerstring · enumRequiredPossible values:

Responses

200

Audio file link

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/tts_trans

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/tts_trans HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 118

{
  "input_text": "Who are you and how are you doing?",
  "src_lang_code": "eng",
  "tgt_lang_code": "hin",
  "input_speaker": "male"
}

{
  "status": "success",
  "data": {
    "audio_file": "https://.../audio-translate-67890.wav"
  }
}

Speech to Text (upload)

post

Upload a short audio file (mp3, wav) and get transcribed text.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

filestring · binaryRequired

Audio file (mp3 or wav).

lang_codestring · enumRequired

Language code

Possible values:

Responses

200

Transcribed text

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/transcribe/upload

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/transcribe/upload HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 35

{
  "file": "binary",
  "lang_code": "eng"
}

{
  "status": "success",
  "data": {
    "text": [
      "major exports include petroleum products textile goods jewelry software engineering goods chemicals and manufactured leather goods"
    ]
  }
}

Speech to Text Translation (upload)

post

Upload a short audio file (mp3, wav) and get translated text.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

filestring · binaryRequired

Audio file (mp3 or wav).

src_lang_codestring · enumRequired

Only 'eng' is supported as the source for certain translation endpoints.

Possible values:

tgt_lang_codestring · enumRequired

Target language code

Possible values:

Responses

200

Translated text

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/stt_trans/upload

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/stt_trans/upload HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 61

{
  "file": "binary",
  "src_lang_code": "eng",
  "tgt_lang_code": "eng"
}

{
  "status": "success",
  "data": {
    "translated_text": "प्रमुख निर्यातों में पेट्रोलियम उत्पाद, वस्त्र, आभूषण, सॉफ्टवेयर, इंजीनियरिंग सामान, रसायन और निर्मित चमड़े के सामान शामिल हैं।"
  }
}

Speech to Speech Translation (upload)

post

Upload a short audio file and receive translated synthesized speech.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

filestring · binaryRequired

Audio file (mp3 or wav).

src_lang_codestring · enumRequired

Only 'eng' is supported as the source for certain translation endpoints.

Possible values:

tgt_lang_codestring · enumRequired

Target language code

Possible values:

input_speakerstring · enumRequiredPossible values:

Responses

200

Audio file link

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/sts_trans/upload

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/sts_trans/upload HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 86

{
  "file": "binary",
  "src_lang_code": "eng",
  "tgt_lang_code": "eng",
  "input_speaker": "female"
}

{
  "status": "success",
  "data": {
    "audio_file": "https://.../audio-sts-abc123.wav"
  }
}

Long-duration Speech to Text (upload)

post

Upload a longer audio file for asynchronous transcription; returns a request_id that can be polled.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

filestring · binaryRequired

Audio file (mp3 or wav).

lang_codestring · enumRequired

Language code

Possible values:

Responses

200

Job queued

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/transcribe/lf/upload

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/transcribe/lf/upload HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 35

{
  "file": "binary",
  "lang_code": "eng"
}

{
  "status": "success",
  "data": {
    "request_id": "7b9a9d93-1f0b-4a9a-8e7d-9a5f2c8c1d23",
    "status": "QUEUED"
  }
}

Long-duration Speech to Text Translation (upload)

post

Upload a longer audio file for asynchronous speech-to-text translation; returns a request_id that can be polled.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

multipart/form-data

filestring · binaryRequired

Long audio file (mp3 or wav).

src_lang_codestring · enumRequired

Only 'eng' is supported as the source for certain translation endpoints.

Possible values:

tgt_lang_codestring · enumRequired

Target language code

Possible values:

Responses

200

Job queued

application/json

400

Bad request

application/json

401

Unauthorized

application/json

post

/languagelabs/stt_trans/lf/upload

HTTPcURLJavaScriptPython

POST /api/v1/languagelabs/stt_trans/lf/upload HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 61

{
  "file": "binary",
  "src_lang_code": "eng",
  "tgt_lang_code": "eng"
}

{
  "status": "success",
  "data": {
    "request_id": "b1a2a3b4-c5d6-7890-1234-abcdef987654",
    "status": "QUEUED"
  }
}

Get long-duration job status

get

Poll the status of a long-duration transcription/translation job and obtain the output link/text when available.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Path parameters

request_idstringRequired

Request ID returned by the long-duration upload endpoint.

Responses

200

Job status payload

application/json

400

Bad request

application/json

401

Unauthorized

application/json

404

Request ID not found

application/json

get

/languagelabs/job_status/{request_id}

HTTPcURLJavaScriptPython

GET /api/v1/languagelabs/job_status/{request_id} HTTP/1.1
Host: cloud.olakrutrim.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "status": "success",
  "data": {
    "request_id": "12345678-4406-4931-8138-f64af4de82c2",
    "file_name": "dummy_file_name-2024-9-30-12-46-43.wav",
    "file_size_mb": 2.690715789794922,
    "service_type": "stttransservice",
    "status": "SUCCESS",
    "output_file": "https://.../output-123456.txt",
    "created_at": "2024-10-03T14:14:03.737880",
    "updated_at": "2024-10-03T14:14:04.017735"
  }
}