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

# Boole AI Audio Transcriptions – Whisper Large v3 Endpoint

> Transcribe audio files with the Boole AI Whisper Large v3 endpoint — accepted formats, multipart request parameters, response schema, and pricing.

The `/v1/audio/transcriptions` endpoint transcribes audio files using Whisper Large v3 — optimized by the Boole compiler for fast inference. Submit an audio file and receive a text transcript. The endpoint accepts a wide range of audio formats and supports automatic language detection, custom prompts for improved accuracy, and multiple output formats including plain text, SRT, and VTT.

## Endpoint

```
POST https://api.boole.dev/v1/audio/transcriptions
```

## Request

Send requests as `multipart/form-data`.

<ParamField body="file" type="file" required>
  The audio file to transcribe. Supported formats: `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `wav`, `webm`. Maximum file size: **25 MB**.
</ParamField>

<ParamField body="model" type="string" required>
  Must be `whisper-large-v3`.
</ParamField>

<ParamField body="language" type="string">
  ISO-639-1 language code of the spoken language, e.g. `en`, `fr`, `de`. When omitted, the language is detected automatically from the audio.
</ParamField>

<ParamField body="prompt" type="string">
  Optional text to guide the model's style or supply context, such as proper nouns or domain-specific vocabulary. Does not need to match the spoken language.
</ParamField>

<ParamField body="response_format" type="string">
  Format of the transcript output. One of: `json` (default), `text`, `srt`, `vtt`, or `verbose_json`. `verbose_json` includes segment-level timestamps and metadata.
</ParamField>

<ParamField body="temperature" type="number">
  Sampling temperature between `0` and `1`. At `0` (default), the model uses greedy decoding for the most deterministic output.
</ParamField>

## Example Request

```bash theme={null}
curl https://api.boole.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer $BOOLE_API_KEY" \
  -F file=@recording.mp3 \
  -F model=whisper-large-v3
```

## Example Response

```json theme={null}
{
  "text": "The quick brown fox jumps over the lazy dog."
}
```

## Pricing

Whisper Large v3 is billed at **\$0.02 per minute** of audio, rounded up to the nearest second. See [Pricing](/concepts/pricing) for the full rate card and details on how audio duration is measured.

<Tip>
  Pass a `language` code when you know the spoken language — it improves accuracy and reduces latency.
</Tip>