README.md

---
title: OLLAMA
emoji: 🎤
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
---

# OLLAMA

A high-performance speech-to-text API built with FastAPI and faster-whisper.

## Features

- 🚀 Fast transcription
- 🌍 Auto language detection
- 🇮🇳 Hindi
- 🇬🇧 English
- 🔀 Hinglish
- 🎤 MP3, WAV, M4A, OGG, WebM, FLAC support

## API

### GET /

Returns API status.

### POST /transcribe

Upload an audio file using `multipart/form-data`.

Field name:

```
file
```

Example response:

```json
{
  "success": true,
  "language": "hi",
  "language_probability": 0.998,
  "text": "Hello bhai kaise ho"
}
```