> ## 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.

# Quickstart

> Get started with transcribing pre-recorded audio files using the Waves STT API

This guide shows you how to convert an audio file into text using Smallest AI's Pulse STT model.

# Pre-Recorded Audio

> Transcribe pre-recorded audio files using synchronous HTTPS POST requests. Perfect for batch processing, archived media, and offline transcription workflows.

The Pre-Recorded API allows you to upload audio files and receive complete transcripts in a single request. It can process an audio file uploaded as raw bytes or take a URL to retrieve one from a remote server.

## When to Use Pre-Recorded Transcription

* **Batch processing**: Transcribe multiple audio files at once
* **Archived media**: Process existing recordings, podcasts, or videos
* **Offline workflows**: Upload files that are already stored locally or in cloud storage
* **Complete transcripts**: When you need the full transcription before proceeding

## Endpoint

```
POST https://api.smallest.ai/waves/v1/pulse/get_text
```

## Authentication

Head over to the [smallest console](https://app.smallest.ai/dashboard/settings/apikeys) to generate an API key, if not done previously. Also look at [Authentication guide](/v4.0.0/content/getting-started/authentication) for more information about API keys and their usage.

Include your API key in the Authorization header:

```http theme={null}
Authorization: Bearer SMALLEST_API_KEY
```

## Example Request

The API supports two input methods: **Raw Audio Bytes** and **Audio URL**. For details on both methods, see the [Audio Specifications](/v4.0.0/content/speech-to-text/pre-recorded/audio-formats) guide.

### Method 1: Raw Audio Bytes

Upload audio files directly by sending raw audio data:

<CodeGroup>
  ```bash cURL theme={null}
  curl --request POST \
    --url "https://api.smallest.ai/waves/v1/pulse/get_text?language=en&word_timestamps=true" \
    --header "Authorization: Bearer $SMALLEST_API_KEY" \
    --header "Content-Type: audio/wav" \
    --data-binary "@/path/to/audio.wav"
  ```

  ```python Python theme={null}
  import os
  import requests

  API_KEY = os.environ["SMALLEST_API_KEY"]
  endpoint = "https://api.smallest.ai/waves/v1/pulse/get_text"
  params = {
      "language": "en",
      "word_timestamps": "true",
  }
  headers = {
      "Authorization": f"Bearer {API_KEY}",
      "Content-Type": "audio/wav",
  }

  with open("sample.wav", "rb") as audio:
      response = requests.post(endpoint, params=params, headers=headers, data=audio.read(), timeout=120)

  response.raise_for_status()
  result = response.json()
  print(result["transcription"])
  ```

  ```javascript JavaScript theme={null}
  import fetch from "node-fetch";
  import fs from "fs";

  const endpoint = "https://api.smallest.ai/waves/v1/pulse/get_text";
  const params = new URLSearchParams({
    language: "en",
    word_timestamps: "true",
  });

  const audioBuffer = fs.readFileSync("sample.wav");

  const response = await fetch(`${endpoint}?${params}`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.SMALLEST_API_KEY}`,
      "Content-Type": "audio/wav",
    },
    body: audioBuffer,
  });

  if (!response.ok) throw new Error(await response.text());
  const data = await response.json();
  console.log(data.transcription);
  ```
</CodeGroup>

### Method 2: Audio URL

Provide a URL to an audio file hosted remotely. This is useful when your audio files are stored in cloud storage (S3, Google Cloud Storage, etc.) or accessible via HTTP/HTTPS:

<CodeGroup>
  ```bash cURL theme={null}
  curl --request POST \
    --url "https://api.smallest.ai/waves/v1/pulse/get_text?language=en&word_timestamps=true" \
    --header "Authorization: Bearer $SMALLEST_API_KEY" \
    --header "Content-Type: application/json" \
    --data '{
      "url": "https://example.com/audio.mp3"
    }'
  ```

  ```python Python theme={null}
  import os
  import requests

  API_KEY = os.environ["SMALLEST_API_KEY"]
  endpoint = "https://api.smallest.ai/waves/v1/pulse/get_text"
  params = {
      "language": "en",
      "word_timestamps": "true",
  }
  headers = {
      "Authorization": f"Bearer {API_KEY}",
      "Content-Type": "application/json",
  }
  body = {
      "url": "https://example.com/audio.mp3"
  }

  response = requests.post(endpoint, params=params, headers=headers, json=body, timeout=120)
  response.raise_for_status()
  result = response.json()
  print(result["transcription"])
  ```

  ```javascript JavaScript theme={null}
  import fetch from "node-fetch";

  const endpoint = "https://api.smallest.ai/waves/v1/pulse/get_text";
  const params = new URLSearchParams({
    language: "en",
    word_timestamps: "true",
  });

  const response = await fetch(`${endpoint}?${params}`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.SMALLEST_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      url: "https://example.com/audio.mp3"
    }),
  });

  if (!response.ok) throw new Error(await response.text());
  const data = await response.json();
  console.log(data.transcription);
  ```
</CodeGroup>

## Example Response

A successful request returns a JSON object with the transcription:

```json theme={null}
{
  "status": "success",
  "transcription": "Hello, this is a test transcription.",
  "words": [
    {"start": 0.48, "end": 1.12, "word": "Hello,"},
    {"start": 1.12, "end": 1.28, "word": "this"},
    {"start": 1.28, "end": 1.44, "word": "is"},
    {"start": 1.44, "end": 2.16, "word": "a"},
    {"start": 2.16, "end": 2.96, "word": "test"},
    {"start": 2.96, "end": 3.76, "word": "transcription."}
  ],
  "utterances": [
    {"start": 0.48, "end": 3.76, "text": "Hello, this is a test transcription."}
  ]
}
```

## Next Steps

* Learn about [supported audio formats](/v4.0.0/content/speech-to-text/pre-recorded/audio-formats).
* Decide which enrichment options to enable in the [features guide](/v4.0.0/content/speech-to-text/pre-recorded/features).
* Configure asynchronous callbacks with [webhooks](/v4.0.0/content/speech-to-text/pre-recorded/webhooks).
* Review a full [code example](/v4.0.0/content/speech-to-text/pre-recorded/code-examples) here.