> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nano-gpt.com/llms.txt
> Use this file to discover all available pages before exploring further.

# v1/audio/transcriptions (STT)

> OpenAI-compatible speech-to-text transcription endpoint

## Overview

NanoGPT provides a drop-in OpenAI-compatible endpoint for speech-to-text (STT) transcription.

## Endpoint

```text theme={null}
POST https://nano-gpt.com/api/v1/audio/transcriptions
```

## Authentication

Use either header:

* `Authorization: Bearer YOUR_API_KEY`
* `x-api-key: YOUR_API_KEY`

## Request Formats

### 1) Multipart upload (OpenAI-compatible)

Send `multipart/form-data` with:

* `file` (required): audio (or video for supported models)
* `model` (required): STT model ID
* `language` (optional): language code (default: auto-detect)

```bash theme={null}
curl -X POST https://nano-gpt.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file=@audio.mp3 \
  -F model=Whisper-Large-V3 \
  -F language=en
```

### 2) JSON with URL

```json theme={null}
{
  "model": "Whisper-Large-V3",
  "file_url": "https://example.com/audio.mp3",
  "language": "en"
}
```

NanoGPT accepts `file_url` or `audio_url` for URL-based transcription.

## Supported Models (Examples)

Model availability changes; use `GET /api/v1/models?detailed=true` for discovery.

| Model                       | Notes                                        |
| --------------------------- | -------------------------------------------- |
| `Whisper-Large-V3`          | High-accuracy transcription                  |
| `Wizper`                    | Fast processing                              |
| `Elevenlabs-STT`            | Speaker diarization + audio event tagging    |
| `gpt-4o-mini-transcribe`    | Improved accuracy vs Whisper (OpenAI-family) |
| `openai-whisper-with-video` | Accepts video files (MP4, MOV, etc.)         |

### Voice Cloning (via the same endpoint)

Some special model IDs run voice-cloning workflows instead of returning plain transcription text:

* `qwen-voice-clone` — returns a reusable speaker embedding URL
* `minimax-voice-clone` — returns a reusable custom voice ID (and/or preview output)

## Response

```json theme={null}
{
  "text": "The transcribed text goes here.",
  "language": "en",
  "duration": 45.2
}
```

## Supported Formats

* Audio: MP3, OGG, WAV, M4A, AAC
* Video (model-dependent): MP4, MOV, AVI, MKV, WEBM

## Example (Python, OpenAI SDK)

```python theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="https://nano-gpt.com/api/v1",
    api_key="YOUR_API_KEY"
)

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="Whisper-Large-V3",
        file=audio_file
    )

print(transcript.text)
```

## See Also

* NanoGPT transcription workflows: `api-reference/endpoint/transcribe.mdx`
* Full STT guide and model list: `api-reference/speech-to-text.mdx`