> ## 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. # Upload Transcript > **Optional.** Use this only if you already have the transcript and do not want EkaScribe to transcribe audio for you. Instead of uploading audio files, create a session, POST your transcript here along with the `template_id` you want it structured into, then poll Get Session for the structured result. The call is asynchronous: it returns `202` with a `document_id` and `status: in-progress`. Fetch the structured note with `GET /voice/v1/sessions/{session_id}` (optionally `?document_id=`) or Get Document once its status is `success`. You may also omit `template_id` and send `target_language` instead to translate the transcript (or the session's stored transcript) into another language. **This API is optional.** Use it only when you already have the transcript and don't need EkaScribe to transcribe audio for you. Instead of uploading audio, you post the transcript text plus the `template_id` you want it structured into, and EkaScribe returns the structured note. The flow is three calls — no audio upload, no [End Session](/ekascribe/api-reference/sessions/end-session): ``` 1. Create Session POST /voice/v1/sessions → session_id 2. Upload Transcript POST /voice/api/v1/transaction/{session_id}/convert-to-template { "transcript": "...", "template_id": "..." } → 202, document_id 3. Get Session GET /voice/v1/sessions/{session_id} (poll ~1s until ≠202) → structured note for that template ``` ```bash theme={null} curl -X POST "https://api.eka.care/voice/api/v1/transaction/{session_id}/convert-to-template" \ -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "transcript": "Doctor: What brings you in today?\nPatient: I have had a dry cough and mild fever for three days.", "template_id": "clinical_notes_template" }' ``` The call is asynchronous — it returns `202` with a `document_id`. Poll [Get Session](/ekascribe/api-reference/sessions/get-session) (optionally `?document_id=`) or [Get Document](/ekascribe/api-reference/documents/get-document) until the document's status is `success`. If you omit `template_id`, the template requested in [Create Session](/ekascribe/api-reference/sessions/create-session) (`templates`) is used. To structure the same transcript into more templates later, call [Process Template](/ekascribe/api-reference/sessions/process-template) — each one creates its own document. Sending `target_language` instead of `template_id` translates the transcript into that language (`eng`, `hi`, `ta`, `te`, `bn`, `mr`, `gu`, `kn`, `ml`, `pa`, `as`) rather than structuring it into a template. ## OpenAPI ````yaml POST /voice/api/v1/transaction/{session_id}/convert-to-template openapi: 3.0.1 info: title: EkaScribe Protocol API (MedScribeAlliance v0.1) version: '0.1' description: > Session-based medical voice capture API implementing the MedScribeAlliance Protocol v0.1. Discover service capabilities, create a session, stream audio chunks, then end the session to trigger asynchronous transcription and structured-template extraction. servers: - url: https://api.eka.care description: Production server - url: https://api.dev.eka.care description: Development server security: [] paths: /voice/api/v1/transaction/{session_id}/convert-to-template: post: tags: - sessions summary: Upload Transcript description: > **Optional.** Use this only if you already have the transcript and do not want EkaScribe to transcribe audio for you. Instead of uploading audio files, create a session, POST your transcript here along with the `template_id` you want it structured into, then poll Get Session for the structured result. The call is asynchronous: it returns `202` with a `document_id` and `status: in-progress`. Fetch the structured note with `GET /voice/v1/sessions/{session_id}` (optionally `?document_id=`) or Get Document once its status is `success`. You may also omit `template_id` and send `target_language` instead to translate the transcript (or the session's stored transcript) into another language. parameters: - name: session_id in: path required: true description: Session ID returned by Create Session schema: type: string example: ses_abc123def456 requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/UploadTranscriptRequest' example: transcript: > Doctor: What brings you in today? Patient: I've had a dry cough and mild fever for the last three days. Doctor: Any breathlessness or chest pain? Patient: No, just the cough and I feel tired. template_id: clinical_notes_template responses: '202': description: Transcript accepted, template generation started content: application/json: schema: $ref: '#/components/schemas/UploadTranscriptResponse' example: status: in-progress message: Template generation started in background txn_id: ses_abc123def456 b_id: '123456' template_id: clinical_notes_template document_id: doc_9f8e7d6c templates: - template_id: clinical_notes_template document_id: doc_9f8e7d6c '400': description: Neither `transcript` nor `target_language` was provided content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Session not found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - auth: [] components: schemas: UploadTranscriptRequest: type: object description: > Send at least one of `transcript` or `target_language`. If both are omitted the request is rejected with `400`. properties: transcript: type: string description: > The plain-text transcript of the consultation. This replaces EkaScribe's own transcription — no audio upload is needed for the session. example: > Doctor: What brings you in today? Patient: I've had a dry cough and mild fever for the last three days. template_id: type: string description: > Template to structure the transcript into (from List Templates). If omitted, the template requested in Create Session (`templates`) is used. example: clinical_notes_template target_language: type: string description: > Translate the transcript into this language instead of structuring it into a template. One of `eng`, `hi`, `ta`, `te`, `bn`, `mr`, `gu`, `kn`, `ml`, `pa`, `as`. example: hi UploadTranscriptResponse: type: object properties: status: type: string example: in-progress message: type: string example: Template generation started in background txn_id: type: string description: The session ID the transcript was uploaded to. example: ses_abc123def456 b_id: type: string description: Business ID resolved from your access token. example: '123456' template_id: type: string example: clinical_notes_template document_id: type: string description: >- ID of the document being generated. Poll Get Session or Get Document until its status is `success`. example: doc_9f8e7d6c templates: type: array description: Documents created for this request. items: type: object properties: template_id: type: string document_id: type: string ErrorResponse: type: object properties: error: type: object properties: code: type: string description: Machine-readable error code. example: invalid_audio_format message: type: string description: Human-readable error message. example: Audio format 'audio/mp3' is not supported details: type: object additionalProperties: true description: Additional error context. securitySchemes: auth: type: http scheme: bearer bearerFormat: JWT description: >- Bearer authentication header of the form `Bearer `, where `` is your auth token. ````