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 audio accepted — it does not start transcription yet. Call Start Job next.

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

Authenticated private bucket access is not supported. The Try it playground uses the public URL (application/json) body below. For file upload, use the multipart cURL examples.

Authentication

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

Request Body

Public URL (`application/json`) — Try it

Field	Type	Required	Description
`config.model`	string	Yes	`"gnani-prisma-v2.5"`
`config.language_code`	string	Yes	e.g. `en-IN`
`config.mode`	string	No	`"transcribe"`
`config.with_diarization`	boolean	No	Default `false`
`config.num_speakers`	integer	No	Required when diarization is on (max `2`)
`config.is_multi_channel`	boolean	No	Default `false`
`source.type`	string	Yes	`"cloud_storage"`
`source.auth.mode`	string	Yes	`"public"`
`source.paths`	string[]	Yes	Public HTTPS URLs
`callback_url`	string	No	Webhook URL — leave empty in Try it if unused

URLs are validated at Start Job, not at create.

Multipart upload (`multipart/form-data`)

Use cURL / your client — not the Try it panel.

Field	Type	Required	Description
`config`	string (JSON)	Yes	STT config. Required: `model`, `language_code`. Optional: `mode` (default `transcribe`), `with_diarization`, `num_speakers` (required when diarization is on, max `2`), `is_multi_channel`
`files`	file	Yes	Audio or ZIP. Max 100 files/job, 10 MB/file, ZIP up to 50 MB compressed
`callback_url`	string	No	HTTPS webhook. See Webhook sample payloads

Send config as a form field with Content-Type: application/json (see cURL -F '...;type=application/json').

Example cURL

Direct upload (live-verified)

curl --request POST \
  --url https://api.vachana.ai/stt/v3/batch/jobs \
  --header '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 --request POST \
  --url https://api.vachana.ai/stt/v3/batch/jobs \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key-ID: <YOUR_API_KEY>' \
  --data '{
    "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"]
    }
  }'

Diarization (2 speakers)

curl --request POST \
  --url https://api.vachana.ai/stt/v3/batch/jobs \
  --header 'X-API-Key-ID: <YOUR_API_KEY>' \
  -F 'config={"model":"gnani-prisma-v2.5","language_code":"en-IN","mode":"transcribe","with_diarization":true,"num_speakers":2};type=application/json' \
  -F "files=@./stereo_call.wav"

Response

Success — multipart upload (`201`)

{
  "job_id": "019fa79e-81f9-7a8a-a446-6eff16ddec30",
  "status": "CREATED",
  "total_files_accepted": 1,
  "created_at": "2026-07-28T07:26:50.926489Z",
  "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/...)

Success — public URL create (`201`)

{
  "job_id": "019fa79c-ec88-770c-b498-371fc21fb40e",
  "status": "CREATED",
  "created_at": "2026-07-28T07:25:07.137907Z",
  "message": "Job created. Call POST /stt/v3/batch/jobs/{job_id}/start to begin processing.",
  "total_files_accepted": null
}

Error responses

401 Missing API key

{
  "detail": {
    "error_code": "MISSING_API_KEY",
    "message": "Missing API key",
    "status_code": 401
  }
}

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"
}

string

Unique job identifier. Required for Start / Status / Files / Cancel.

string

Always CREATED on success.

integer

Number of files accepted for multipart/ZIP uploads. May be null for public-URL creates.

Webhook samples

If you pass callback_url, Gnani sends a POST to your URL when the job finishes. Full payload examples (including transcripts[] / full_transcript): → Webhook samples on Batch STT Introduction Events: job.completed · job.partial_failure · job.failed · job.cancelled

Use Cases

Uploading one or many call recordings for offline transcription
Sending a ZIP of customer audio for batch processing
Pointing to public HTTPS / S3 presigned URLs without re-uploading files

Next: Start Job

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

Batch STT Introduction Start Job

Gnani APIs

APIs

Use Cases

Create Job

Overview

Authentication

Request Body

Public URL (`application/json`) — Try it

Multipart upload (`multipart/form-data`)

Example cURL

Direct upload (live-verified)

Public URL

Diarization (2 speakers)

Response

Success — multipart upload (`201`)

Success — public URL create (`201`)

Error responses

Webhook samples

Use Cases

Authorizations

Body

Response

​Overview

​Authentication

​Request Body

​Public URL (application/json) — Try it

​Multipart upload (multipart/form-data)

​Example cURL

​Direct upload (live-verified)

​Public URL

​Diarization (2 speakers)

​Response

​Success — multipart upload (201)

​Success — public URL create (201)

​Error responses

​Webhook samples

​Use Cases

Authorizations

Body

Response

Overview

Authentication

Request Body

Public URL (`application/json`) — Try it

Multipart upload (`multipart/form-data`)

Example cURL

Direct upload (live-verified)

Public URL

Diarization (2 speakers)

Response

Success — multipart upload (`201`)

Success — public URL create (`201`)

Error responses

Webhook samples

Use Cases