---
title: "Transcribe Audio"
method: POST
path: "/voice/transcribe"
tags: ["Voice Input"]
---

# Transcribe Audio

`POST /voice/transcribe`

## Request

- Base URL: `https://api.alpha-grid.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.alpha-grid.ai/voice/transcribe`
- Auth: HTTP bearer

Transcribe audio to text using Sarvam AI.

Supports multiple Indian languages and English:
- hi-IN: Hindi
- en-IN: English (Indian)
- ta-IN: Tamil
- te-IN: Telugu
- kn-IN: Kannada
- ml-IN: Malayalam
- mr-IN: Marathi
- gu-IN: Gujarati
- bn-IN: Bengali
- pa-IN: Punjabi
- or-IN: Odia
- unknown: Auto-detect

Supported audio formats: WAV, MP3, AAC, OGG, OPUS, FLAC, MP4/M4A, WebM

## Request body `multipart/form-data`

- BodyTranscribeAudioVoiceTranscribePost
  - `file` string, binary, required: Audio file to transcribe
  - `language_code` string, nullable: Language code (e.g., 'hi-IN', 'en-IN', 'unknown' for auto-detect)
  - `purpose` string, nullable: Purpose: 'clinical_notes', 'chatbot', or 'general'

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/alpha-grid/apis/alphagrid-backend-dev.md) - [All operations](https://skmtc.dev/alpha-grid/apis/alphagrid-backend-dev/llms.txt) - [OpenAPI document](https://skmtc.dev/alpha-grid/apis/alphagrid-backend-dev/revisions/13bab0bdd466?raw)