Create Job

curl --request POST \
  --url https://api.vachana.ai/stt/v3/batch/jobs \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key-ID: <api-key>' \
  --data '
{
  "config": {
    "model": "gnani-prisma-v2.5",
    "language_code": "en-IN",
    "mode": "transcribe",
    "with_diarization": false,
    "is_multi_channel": false
  },
  "source": {
    "type": "cloud_storage",
    "auth": {
      "mode": "public"
    },
    "paths": [
      "https://cdn.example.com/audio/call-001.mp3"
    ]
  }
}
'

import requests

url = "https://api.vachana.ai/stt/v3/batch/jobs"

payload = {
    "config": {
        "model": "gnani-prisma-v2.5",
        "language_code": "en-IN",
        "mode": "transcribe",
        "with_diarization": False,
        "is_multi_channel": False
    },
    "source": {
        "type": "cloud_storage",
        "auth": { "mode": "public" },
        "paths": ["https://cdn.example.com/audio/call-001.mp3"]
    }
}
headers = {
    "X-API-Key-ID": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key-ID': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    config: {
      model: 'gnani-prisma-v2.5',
      language_code: 'en-IN',
      mode: 'transcribe',
      with_diarization: false,
      is_multi_channel: false
    },
    source: {
      type: 'cloud_storage',
      auth: {mode: 'public'},
      paths: ['https://cdn.example.com/audio/call-001.mp3']
    }
  })
};

fetch('https://api.vachana.ai/stt/v3/batch/jobs', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "job_id": "019fa854-1db0-7e45-a026-7a6b09ff6d7c",
  "status": "CREATED",
  "created_at": "2026-07-28T10:45:12.769450Z",
  "message": "Job created. Call POST /stt/v3/batch/jobs/{job_id}/start to begin processing.",
  "total_files_accepted": null
}

POST

stt

batch

jobs

Create Job

curl --request POST \
  --url https://api.vachana.ai/stt/v3/batch/jobs \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key-ID: <api-key>' \
  --data '
{
  "config": {
    "model": "gnani-prisma-v2.5",
    "language_code": "en-IN",
    "mode": "transcribe",
    "with_diarization": false,
    "is_multi_channel": false
  },
  "source": {
    "type": "cloud_storage",
    "auth": {
      "mode": "public"
    },
    "paths": [
      "https://cdn.example.com/audio/call-001.mp3"
    ]
  }
}
'

import requests

url = "https://api.vachana.ai/stt/v3/batch/jobs"

payload = {
    "config": {
        "model": "gnani-prisma-v2.5",
        "language_code": "en-IN",
        "mode": "transcribe",
        "with_diarization": False,
        "is_multi_channel": False
    },
    "source": {
        "type": "cloud_storage",
        "auth": { "mode": "public" },
        "paths": ["https://cdn.example.com/audio/call-001.mp3"]
    }
}
headers = {
    "X-API-Key-ID": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key-ID': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    config: {
      model: 'gnani-prisma-v2.5',
      language_code: 'en-IN',
      mode: 'transcribe',
      with_diarization: false,
      is_multi_channel: false
    },
    source: {
      type: 'cloud_storage',
      auth: {mode: 'public'},
      paths: ['https://cdn.example.com/audio/call-001.mp3']
    }
  })
};

fetch('https://api.vachana.ai/stt/v3/batch/jobs', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "job_id": "019fa854-1db0-7e45-a026-7a6b09ff6d7c",
  "status": "CREATED",
  "created_at": "2026-07-28T10:45:12.769450Z",
  "message": "Job created. Call POST /stt/v3/batch/jobs/{job_id}/start to begin processing.",
  "total_files_accepted": null
}

Overview

Create a new batch transcription job. The job is created in CREATED status with your files accepted — it does not start transcription yet. Call Start Job after create.

Method	Best for	Content-Type
Direct upload	Files on your machine / CI	`multipart/form-data`
ZIP upload	Many files in one archive	`multipart/form-data`
Public URL	HTTPS links, including S3 presigned URLs	`application/json`

Authenticated private bucket access is not supported.

Authentication

Header	Required	Description
`X-API-Key-ID`	Yes	Your Gnani Prisma v2.5 API key

Request Body

Multipart upload (`multipart/form-data`)

Field	Type	Required	Description
`config`	object (JSON)	Yes	See Configuration
`files`	file	Yes	Audio or ZIP. Repeat the field for multiple files
`callback_url`	string	No	HTTPS webhook URL

Public URL (`application/json`)

Field	Type	Required	Description
`config`	object	Yes	STT config object
`source.type`	string	Yes	`"cloud_storage"`
`source.auth.mode`	string	Yes	`"public"`
`source.paths`	string[]	Yes	HTTPS URLs
`callback_url`	string	No	Webhook URL

Example cURL

Direct upload

curl -X POST "https://api.vachana.ai/stt/v3/batch/jobs" \
  -H "X-API-Key-ID: <YOUR_API_KEY>" \
  -F 'config={"model":"gnani-prisma-v2.5","language_code":"en-IN","mode":"transcribe","with_diarization":false,"is_multi_channel":false};type=application/json' \
  -F "files=@./customer_call.wav"

Public URL

curl -X POST "https://api.vachana.ai/stt/v3/batch/jobs" \
  -H "Content-Type: application/json" \
  -H "X-API-Key-ID: <YOUR_API_KEY>" \
  -d '{
    "config": {
      "model": "gnani-prisma-v2.5",
      "language_code": "en-IN",
      "mode": "transcribe"
    },
    "source": {
      "type": "cloud_storage",
      "auth": { "mode": "public" },
      "paths": ["https://cdn.example.com/audio/call-001.mp3"]
    }
  }'

Response

Success (201)

{
  "job_id": "019fa259-b084-71eb-94d7-ba4cdf2e64c6",
  "status": "CREATED",
  "total_files_accepted": 1,
  "created_at": "2026-07-27T06:53:34.750193Z",
  "message": "1 file(s) uploaded. Call POST /v1/jobs/{job_id}/start to begin processing."
}

Save job_id. Always start with:

POST /stt/v3/batch/jobs/{job_id}/start

(even if the message mentions /v1/jobs/...)

Error responses

400 Unsupported language

{
  "error": "UNSUPPORTED_LANGUAGE",
  "message": "Value error, This service does not support language_code 'xx-XX'. Supported languages: bn-BD, bn-IN, en-IN, hi-IN, kn-IN, ml-IN, mr-IN, ta-IN, te-IN"
}

Next steps

Start Job
Get Job Status — poll until terminal
Get Job Files — then GET each transcript_url

Use the playground on the right to try this endpoint with your API key.

Authorizations

X-API-Key-ID

string

header

required

Your Gnani Prisma v2.5 API key

Body

application/json

config

object

required

Show child attributes

source

object

required

Show child attributes

callback_url

string<uri>

Optional HTTPS webhook URL for terminal job results

Response

Job created

job_id

string<uuid>

status

string

Example:

"CREATED"

created_at

string<date-time>

message

string

total_files_accepted

integer | null

Gnani APIs

APIs

Use Cases

Create Job

Overview

Authentication

Request Body

Multipart upload (`multipart/form-data`)

Public URL (`application/json`)

Example cURL

Direct upload

Public URL

Response

Success (201)

Error responses

Next steps

Authorizations

Body

Response

​Overview

​Authentication

​Request Body

​Multipart upload (multipart/form-data)

​Public URL (application/json)

​Example cURL

​Direct upload

​Public URL

​Response

​Success (201)

​Error responses

​Next steps

Authorizations

Body

Response

Overview

Authentication

Request Body

Multipart upload (`multipart/form-data`)

Public URL (`application/json`)

Example cURL

Direct upload

Public URL

Response

Success (201)

Error responses

Next steps