> ## Documentation Index
> Fetch the complete documentation index at: https://smallestai-ff1e543d.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Audio Specifications

> Supported formats, codecs, and recommendations for pre-recorded audio

## Input Methods

Our API supports two input methods for transcribing audio:

<table style={{ borderCollapse: 'separate', borderSpacing: 0, width: '100%', borderRadius: '8px', overflow: 'hidden' }}>
  <thead>
    <tr style={{ backgroundColor: 'rgba(255, 255, 255, 0.08)' }}>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderTopLeftRadius: '8px' }}>Method</th>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Content Type</th>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderTopRightRadius: '8px' }}>Use Case</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><strong>Raw Bytes</strong></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>application/octet-stream</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Upload audio files directly from your system</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderBottomLeftRadius: '8px' }}><strong>Audio URL</strong></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>application/json</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderBottomRightRadius: '8px' }}>Process audio files hosted on a remote server</td>
    </tr>
  </tbody>
</table>

## Supported Formats

The Pulse STT API supports a wide range of audio formats for pre-recorded transcription.

<table style={{ borderCollapse: 'separate', borderSpacing: 0, width: '100%', borderRadius: '8px', overflow: 'hidden' }}>
  <thead>
    <tr style={{ backgroundColor: 'rgba(255, 255, 255, 0.08)' }}>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderTopLeftRadius: '8px' }}>Format</th>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Extension</th>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Codec</th>
      <th style={{ padding: '12px 16px', textAlign: 'left', fontWeight: '800', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderTopRightRadius: '8px' }}>Notes</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>WAV</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.wav</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>PCM, Linear PCM</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Recommended for best quality</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>MP3</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.mp3</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>MPEG Audio Layer III</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Widely compatible</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>FLAC</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.flac</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Free Lossless Audio Codec</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Lossless compression</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>OGG</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.ogg</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Vorbis, Opus</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Open source format</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>M4A</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.m4a</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>AAC, ALAC</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Apple format</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderBottomLeftRadius: '8px' }}>WebM</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}><code>.webm</code></td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)' }}>Opus, Vorbis</td>
      <td style={{ padding: '12px 16px', border: '0.5px solid rgba(209, 213, 219, 0.2)', borderBottomRightRadius: '8px' }}>Web-optimized</td>
    </tr>
  </tbody>
</table>

## Audio Requirements

### Sample Rate

* **Recommended**: 16 kHz (16,000 Hz)
* **Supported range**: All frequencies
* **Optimal**: 16 kHz mono for speech recognition

### Channels

Currently we support only single channel transcription. We are bringing in multi-channel support soon.

### Limits

* **Maximum size**: No limit on file size
* **Session timeout**: 10 minutes per Session

It is recommended to split the file into chunks and then upload them in parallel for faster processing.

## Format Recommendations

### Best Quality

Use 16 kHz mono Linear PCM (`audio/wav`) for the optimal mix of accuracy and processing speed. This configuration mirrors Waves’ recommended production setup for real-time speech workloads.

```
Format: WAV (Linear PCM)
Sample Rate: 16 kHz
Channels: Mono
Bit Depth: 16-bit
```

### Balanced (Telephony & Voice)

Use 8 kHz μ-law encoded with 8-bit encoding for low bandwidth usage. It provides standard quality for voice-only applications like phone calls.

```
Format: MP3 or μ-law
Sample Rate: 8 kHz
Channels: Mono
Bitrate: 64–96 kbps
```

### Web-Optimized / High Fidelity

For broadcast, captioning, or multimedia scenarios, it is recommended to capture higher sample rates (44.1–48 kHz). Due to the higher quality requirements, bandwidth and processing times would be on the higher side.

```
Format: WebM (Opus) or FLAC
Sample Rate: 44.1–48 kHz
Channels: Mono or Stereo (downmix before upload)
Bitrate: 96–160 kbps
```