> ## Documentation Index
> Fetch the complete documentation index at: https://developer.eka.care/llms.txt
> Use this file to discover all available pages before exploring further.
# Start Transcription
> Start the transcription process for the uploaded audio files. This endpoint is called after uploading any audio files in S3 bucket for transcription and processing.
This API is deprecated. Please use the new [EkaScribe Protocol APIs](/api-reference/health-ai/ekascribe/protocol/overview) (Create Session → Upload Audio → End Session) or the [SDKs](/api-reference/health-ai/ekascribe/quick-start) instead.
## Available Template IDs
Eka Care supports multiple output templates for different medical documentation needs. Choose the appropriate template ID based on your requirements:
| Template ID | Description | Use Case |
| ------------------------- | ---------------------------------------------------------------- | ----------------------------------------------------- |
| `clinical_notes_template` | Comprehensive clinical notes with structured medical information | General clinical documentation, patient consultations |
| `eka_emr_template` | EMR-compatible format for electronic medical records | Integration with EMR systems |
| `transcript_template` | Basic transcription with minimal structuring | Simple audio-to-text conversion |
## Available model types
| Model Type | Description |
| ---------- | --------------------------------------- |
| pro | Our most accurate model |
| lite | More performant model for lower latency |
## Supported Input Languages
Eka Care supports transcription in multiple languages. Specify the appropriate language ID in the `input_language` parameter:
| Language ID | Language Name |
| ----------- | ----------------------- |
| `en-IN` | English (India) |
| `en-US` | English (United States) |
| `hi` | Hindi |
| `gu` | Gujarati |
| `kn` | Kannada |
| `ml` | Malayalam |
| `ta` | Tamil |
| `te` | Telugu |
| `bn` | Bengali |
| `mr` | Marathi |
| `pa` | Punjabi |
| `or` | Oriya |
## Supported Output Languages
Eka Care supports generating transcription output in multiple languages, but only one can be selected at a time. Specify the appropriate language ID in the `output_language` parameter.
| Language ID | Language Name |
| ----------- | ----------------------- |
| `en-IN` | English (India) |
| `en-US` | English (United States) |
| `hi` | Hindi |
| `gu` | Gujarati |
| `kn` | Kannada |
| `ml` | Malayalam |
| `ta` | Tamil |
| `te` | Telugu |
| `bn` | Bengali |
| `mr` | Marathi |
| `pa` | Punjabi |
| `or` | Oriya |
## OpenAPI
````yaml POST /voice/api/v2/transaction/init/{txn_id}
openapi: 3.0.1
info:
title: EkaScribe Voice API v2
version: '2024-12-01T12:09:09Z'
description: >-
EkaScribe Voice-to-Prescription API for medical transcription and structured
data generation
servers:
- url: https://api.eka.care
description: Production server
- url: https://api.dev.eka.care
description: Development server
security: []
paths:
/voice/api/v2/transaction/init/{txn_id}:
post:
summary: Initialize Transaction
description: >-
Start the transcription process for the uploaded audio files. This
endpoint is called after uploading any audio files in S3 bucket for
transcription and processing.
parameters:
- name: txn_id
in: path
required: true
description: Unique Transaction ID - same as passed in presigned URL request
schema:
type: string
example: test_1234
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- mode
- transfer
- batch_s3_url
- client_generated_files
- model_type
properties:
mode:
type: string
description: Processing mode
enum:
- dictation
- consultation
example: dictation
transfer:
type: string
description: >-
Transfer mode use `vaded` for pre-processed audio with Voice
Activity Detection, `non-vaded` for raw audio files
enum:
- non-vaded
- vaded
example: non-vaded
batch_s3_url:
type: string
description: >
Complete S3 URL path where audio files are uploaded. This is
constructed by combining:
- Base S3 URL from presigned response:
`presigned_url["uploadData"]["url"]`
- Folder path from presigned response:
`presigned_url["folderPath"]`
**Construction:** `presigned_url["uploadData"]["url"] +
presigned_url["folderPath"]`
example: >-
https://m-prod-ekascribe-batch.s3.amazonaws.com/EC_173210496011417/txn_301/20250617_105524/
client_generated_files:
type: array
description: Array of audio file names that were uploaded to S3
items:
type: string
example:
- audio_first.m4a
- audio_second.m4a
model_type:
type: string
description: Type of model to be used for transcription
enum:
- pro
- lite
example: pro
additional_data:
type: object
description: Contextual information for the transaction
additionalProperties: true
example:
doctor:
_id: '174097180967921'
profile:
personal:
name:
f: Divyesh
l: ''
patient: {}
visitid: 09e4f00f-d665-4212-b77c-b2dd5f22bd92_1742560488782
input_language:
type: array
description: Array of supported input languages for voice transcription
items:
type: string
enum:
- en-IN
- en-US
- hi
- gu
- kn
- ml
- ta
- te
- bn
- mr
- pa
- or
example:
- en-IN
output_language:
type: string
description: Output language for the transcription result
enum:
- en-IN
- en-US
- hi
- gu
- kn
- ml
- ta
- te
- bn
- mr
- pa
- or
example: en-IN
speciality:
type: string
description: Medical speciality context for better transcription accuracy
example: general_medicine
output_format_template:
type: array
description: Array of template configurations for output format
items:
type: object
properties:
template_id:
type: string
enum:
- eka_emr_template
- clinical_notes_template
- transcript_template
example: eka_emr_template
codification_needed:
type: boolean
description: Whether codification is needed for the output
example: false
example:
- template_id: eka_emr_template
codification_needed: false
example:
additional_data:
doctor:
_id: '174097180967921'
profile:
personal:
name:
f: Divyesh
l: ''
patient: {}
visitid: 09e4f00f-d665-4212-b77c-b2dd5f22bd92_1742560488782
mode: dictation
input_language:
- en-IN
output_language: en-IN
speciality: general_medicine
output_format_template:
- template_id: eka_emr_template
codification_needed: false
transfer: non-vaded
batch_s3_url: >-
s3://m-pp-voice2rx/250307/R-S3-195D5131-D014-56A8-ACCF-2F8F2D230DEC/
responses:
'201':
description: Transaction initialized successfully
content:
application/json:
schema:
type: object
properties:
status:
type: string
example: success
message:
type: string
example: Transaction initialized successfully
txn_id:
type: string
example: test_1234
b_id:
type: string
example: b-1234567890
'401':
description: Unauthorized - Invalid or missing authentication token
content:
application/json:
schema:
type: object
properties:
error:
type: string
example: Unauthorized
message:
type: string
example: Invalid or missing authentication token
'409':
description: Transaction already initialized with the same session ID
content:
application/json:
schema:
type: object
properties:
status:
type: string
example: error
message:
type: string
example: Transaction already initialized
'422':
description: Missing required fields
content:
application/json:
schema:
type: object
properties:
details:
type: array
items:
type: object
'500':
description: Internal Server Error
content:
application/json:
schema:
type: object
properties:
error:
type: string
description: Error message
code:
type: string
description: Error code
security:
- auth: []
components:
securitySchemes:
auth:
type: http
scheme: bearer
bearerFormat: JWT
description: >-
Bearer authentication header of the form `Bearer `, where
`` is your auth token.
````