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

# CLI Usage

> Use Whisper from the command line for audio transcription and translation

## Overview

The `whisper` command-line tool provides a simple interface for transcribing and translating audio files. It supports multiple audio formats and offers extensive customization options.

## Basic Usage

<Steps>
  <Step title="Install Whisper">
    ```bash theme={null}
    pip install -U openai-whisper
    ```

    You'll also need `ffmpeg` installed on your system:

    <CodeGroup>
      ```bash Ubuntu/Debian theme={null}
      sudo apt update && sudo apt install ffmpeg
      ```

      ```bash macOS theme={null}
      brew install ffmpeg
      ```

      ```bash Windows (Chocolatey) theme={null}
      choco install ffmpeg
      ```
    </CodeGroup>
  </Step>

  <Step title="Transcribe an audio file">
    ```bash theme={null}
    whisper audio.mp3
    ```

    By default, this uses the `turbo` model and outputs all available formats (txt, vtt, srt, tsv, json).
  </Step>
</Steps>

## Command Syntax

```bash theme={null}
whisper [audio_files...] [options]
```

### Multiple Files

Process multiple audio files in one command:

```bash theme={null}
whisper audio.flac audio.mp3 audio.wav --model turbo
```

## Model Selection

Choose from different model sizes to balance speed and accuracy:

```bash theme={null}
whisper audio.mp3 --model medium
```

Available models: `tiny`, `base`, `small`, `medium`, `large`, `turbo`, or English-only variants (`tiny.en`, `base.en`, `small.en`, `medium.en`).

<Note>
  The default model is `turbo`, which offers fast transcription with good accuracy for English and multilingual content.
</Note>

## Language Options

### Automatic Language Detection

By default, Whisper detects the language automatically:

```bash theme={null}
whisper japanese.wav
```

### Specify Language

For better performance, specify the language explicitly:

```bash theme={null}
whisper japanese.wav --language Japanese
```

You can use either the language name (e.g., `Japanese`, `Spanish`) or language code (e.g., `ja`, `es`).

### Translation to English

Translate non-English speech directly to English:

```bash theme={null}
whisper japanese.wav --model medium --language Japanese --task translate
```

<Warning>
  The `turbo` model does **not** support translation. Use multilingual models (`tiny`, `base`, `small`, `medium`, `large`) for translation tasks.
</Warning>

## Output Options

### Output Directory

Specify where to save the transcription files:

```bash theme={null}
whisper audio.mp3 --output_dir ./transcripts
```

### Output Format

Choose specific output formats:

```bash theme={null}
whisper audio.mp3 --output_format srt
```

Available formats:

* `txt` - Plain text
* `vtt` - WebVTT subtitles
* `srt` - SubRip subtitles
* `tsv` - Tab-separated values with timestamps
* `json` - JSON with detailed segment information
* `all` - Generate all formats (default)

## Advanced Options

### Word-Level Timestamps

Extract word-level timestamps for precise timing:

```bash theme={null}
whisper audio.mp3 --word_timestamps True
```

This enables additional subtitle formatting options:

```bash theme={null}
whisper audio.mp3 --word_timestamps True --max_line_width 50 --highlight_words True
```

### Device Selection

Choose between CPU and GPU processing:

```bash theme={null}
whisper audio.mp3 --device cuda  # Use GPU
whisper audio.mp3 --device cpu   # Use CPU
```

### Initial Prompt

Provide context or custom vocabulary to improve accuracy:

```bash theme={null}
whisper audio.mp3 --initial_prompt "This is a technical discussion about machine learning and neural networks."
```

### Temperature and Sampling

<Tabs>
  <Tab title="Greedy Decoding">
    Use temperature 0 for deterministic output:

    ```bash theme={null}
    whisper audio.mp3 --temperature 0 --beam_size 5
    ```
  </Tab>

  <Tab title="Sampling">
    Use non-zero temperature for sampling:

    ```bash theme={null}
    whisper audio.mp3 --temperature 0.8 --best_of 5
    ```
  </Tab>
</Tabs>

### Compression and Quality Thresholds

```bash theme={null}
whisper audio.mp3 \
  --compression_ratio_threshold 2.4 \
  --logprob_threshold -1.0 \
  --no_speech_threshold 0.6
```

* `--compression_ratio_threshold`: Detect and retry overly repetitive outputs (default: 2.4)
* `--logprob_threshold`: Retry if average log probability is too low (default: -1.0)
* `--no_speech_threshold`: Detect silent segments (default: 0.6)

## Common Examples

### Transcribe with High Accuracy

```bash theme={null}
whisper interview.mp3 --model large --language English
```

### Generate SRT Subtitles

```bash theme={null}
whisper video.mp4 --model medium --output_format srt --word_timestamps True
```

### Process Specific Audio Clips

```bash theme={null}
whisper podcast.mp3 --clip_timestamps "0,300,600,900" --output_dir ./segments
```

This processes clips from 0-300s and 600-900s.

### Batch Processing with Consistent Settings

```bash theme={null}
whisper *.wav --model turbo --language English --output_dir ./output --output_format json
```

## Full Options Reference

View all available options:

```bash theme={null}
whisper --help
```

<Tip>
  For large files or batch processing, consider using a GPU with `--device cuda` to significantly speed up transcription.
</Tip>