# Universal 3.5 Pro (`assemblyai/universal-3-5-pro`): API

> assemblyai/universal-3-5-pro is a speech-to-text model from Assemblyai you can call on the OceanToken API.

Endpoint: `POST https://api.oceantoken.ai/v1/audio/transcriptions`, multipart/form-data. Auth: `Authorization: Bearer $OCEANTOKEN_API_KEY`. OpenAI-compatible; the OpenAI SDKs work with base URL https://api.oceantoken.ai/v1.

## Request parameters

- `file` (binary; required): The audio: mp3, m4a, wav, webm and other common formats.
- `model` (string; required): This model's ID.
- `language` (string): ISO-639-1 code such as `en`; improves accuracy.
- `prompt` (string): Names and spellings to expect.
- `response_format` (string; json, text, verbose_json, srt, vtt; default "json"): Models differ in which they offer.

## Example: Transcribe a file

```bash
curl https://api.oceantoken.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $OCEANTOKEN_API_KEY" \
  -F model="assemblyai/universal-3-5-pro" -F file=@meeting.mp3
```

```python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.oceantoken.ai/v1", api_key=os.environ["OCEANTOKEN_API_KEY"])
with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(model="assemblyai/universal-3-5-pro", file=f)
print(result.text)
```

## Response

- `text` (string): The transcript.

```json
{
  "text": "Hello and welcome."
}
```

## More

- Model page: https://docs.oceantoken.ai/models/assemblyai/universal-3-5-pro
- This spec as JSON (with a JSON Schema of the request): https://docs.oceantoken.ai/models/assemblyai/universal-3-5-pro/spec.json
- Guide: https://docs.oceantoken.ai/guides/audio
- All models: https://docs.oceantoken.ai/llms.txt