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

# Convert text to speech

> Generate speech audio from text columns in Pixeltable using OpenAI, ElevenLabs, and other TTS providers via declarative computed columns.

<a href="https://kaggle.com/kernels/welcome?src=https://github.com/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/audio/audio-text-to-speech.ipynb" id="openKaggle" target="_blank" rel="noopener noreferrer"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open in Kaggle" style={{ display: 'inline', margin: '0px' }} noZoom /></a>  <a href="https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/audio/audio-text-to-speech.ipynb" id="openColab" target="_blank" rel="noopener noreferrer"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab" style={{ display: 'inline', margin: '0px' }} noZoom /></a>  <a href="https://raw.githubusercontent.com/pixeltable/pixeltable/refs/tags/release/docs/release/howto/cookbooks/audio/audio-text-to-speech.ipynb" id="downloadNotebook" target="_blank" rel="noopener noreferrer"><img src="https://img.shields.io/badge/%E2%AC%87-Download%20Notebook-blue" alt="Download Notebook" style={{ display: 'inline', margin: '0px' }} noZoom /></a>

<Tip>This documentation page is also available as an interactive notebook. You can launch the notebook in
Kaggle or Colab, or download it for use with an IDE or local Jupyter installation, by clicking one of the
above links.</Tip>

export const quartoRawHtml = [`
<table>
<thead>
<tr>
<th>Use case</th>
<th>Input</th>
<th>Output</th>
</tr>
</thead>
<tbody>
<tr>
<td style="vertical-align: middle;">Accessibility</td>
<td style="vertical-align: middle;">Blog posts</td>
<td style="vertical-align: middle;">Audio articles</td>
</tr>
<tr>
<td style="vertical-align: middle;">Learning</td>
<td style="vertical-align: middle;">Documentation</td>
<td style="vertical-align: middle;">Audio guides</td>
</tr>
<tr>
<td style="vertical-align: middle;">Content</td>
<td style="vertical-align: middle;">Newsletters</td>
<td style="vertical-align: middle;">Podcast episodes</td>
</tr>
</tbody>
</table>
`, `
<table class="dataframe" data-quarto-postprocess="true" data-border="1">
<colgroup>
<col style="width: 33%" />
<col style="width: 33%" />
<col style="width: 33%" />
</colgroup>
<thead>
<tr style="text-align: right;">
<th data-quarto-table-cell-role="th">title</th>
<th data-quarto-table-cell-role="th">content</th>
<th data-quarto-table-cell-role="th">audio</th>
</tr>
</thead>
<tbody>
<tr>
<td style="vertical-align: middle;">Welcome to AI</td>
<td style="vertical-align: middle;">Artificial intelligence is transforming how we work and live. From
smart assistants to autonomous vehicles, AI is becoming part of our
daily lives.</td>
<td style="vertical-align: middle;"><div class="pxt_audio">
<audio controls>
<source src="http://127.0.0.1:52941/Users/pjlb/.pixeltable/media/b448d43a91a64b1581bdb993cbf3b514/f5/f50b/b448d43a91a64b1581bdb993cbf3b514_6_2_f50bc2ab8d874fa1b2ae6e611fa5ae96.mp3" type="audio/mpeg">
</source>
</audio>
</div></td>
</tr>
<tr>
<td style="vertical-align: middle;">Getting Started</td>
<td style="vertical-align: middle;">To begin your journey with machine learning, start by understanding
the basics of data preparation and model training.</td>
<td style="vertical-align: middle;"><div class="pxt_audio">
<audio controls>
<source src="http://127.0.0.1:52941/Users/pjlb/.pixeltable/media/b448d43a91a64b1581bdb993cbf3b514/b2/b2fa/b448d43a91a64b1581bdb993cbf3b514_6_2_b2fa0917c3604279aafe8c1af4f971e2.mp3" type="audio/mpeg">
</source>
</audio>
</div></td>
</tr>
</tbody>
</table>
`, `
<table>
<thead>
<tr>
<th>Model</th>
<th>Speed</th>
<th>Quality</th>
<th>Use case</th>
</tr>
</thead>
<tbody>
<tr>
<td style="vertical-align: middle;"><code>tts-1</code></td>
<td style="vertical-align: middle;">Fast</td>
<td style="vertical-align: middle;">Good</td>
<td style="vertical-align: middle;">Real-time, drafts</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>tts-1-hd</code></td>
<td style="vertical-align: middle;">Slower</td>
<td style="vertical-align: middle;">Higher</td>
<td style="vertical-align: middle;">Production audio</td>
</tr>
</tbody>
</table>
`, `
<table>
<thead>
<tr>
<th>Voice</th>
<th>Style</th>
</tr>
</thead>
<tbody>
<tr>
<td style="vertical-align: middle;"><code>alloy</code></td>
<td style="vertical-align: middle;">Neutral, balanced</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>echo</code></td>
<td style="vertical-align: middle;">Warm, conversational</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>fable</code></td>
<td style="vertical-align: middle;">Expressive, storytelling</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>onyx</code></td>
<td style="vertical-align: middle;">Deep, authoritative</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>nova</code></td>
<td style="vertical-align: middle;">Friendly, upbeat</td>
</tr>
<tr>
<td style="vertical-align: middle;"><code>shimmer</code></td>
<td style="vertical-align: middle;">Clear, professional</td>
</tr>
</tbody>
</table>
`];

Generate natural-sounding audio from text using OpenAI’s text-to-speech
models.

## Problem

You need to convert text content into spoken audio—for accessibility,
content repurposing, or voice applications.

<div style={{ 'margin': '0px 20px 0px 20px' }} dangerouslySetInnerHTML={{ __html: quartoRawHtml[0] }} />

## Solution

**What’s in this recipe:**

* Generate speech with OpenAI TTS
* Choose from multiple voice options
* Store text and audio together

You add a computed column that converts text to audio. The audio is
cached and only regenerated when the source text changes.

### Setup

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
%pip install -qU pixeltable openai
```

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import getpass
import os

if 'OPENAI_API_KEY' not in os.environ:
    os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key: ')
```

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import pixeltable as pxt
from pixeltable.functions.openai import speech

# Create a fresh directory
pxt.drop_dir('tts_demo', force=True)
pxt.create_dir('tts_demo')
```

<pre style={{ 'margin': '-20px 20px 0px 20px', 'padding': '0px', 'background-color': 'transparent', 'color': 'black' }}>
  Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/pjlb/.pixeltable/pgdata
  Created directory 'tts\_demo'.
  \<pixeltable.catalog.dir.Dir at 0x17f0d5bd0>
</pre>

### Create text-to-speech pipeline

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Create table for articles
articles = pxt.create_table(
    'tts_demo/articles', {'title': pxt.String, 'content': pxt.String}
)
```

<pre style={{ 'margin': '-20px 20px 0px 20px', 'padding': '0px', 'background-color': 'transparent', 'color': 'black' }}>
  Created table 'articles'.
</pre>

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Add audio generation column
articles.add_computed_column(
    audio=speech(articles.content, model='tts-1', voice='alloy')
)
```

<pre style={{ 'margin': '-20px 20px 0px 20px', 'padding': '0px', 'background-color': 'transparent', 'color': 'black' }}>
  Added 0 column values with 0 errors.
  No rows affected.
</pre>

### Generate audio

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Insert sample articles
sample_articles = [
    {
        'title': 'Welcome to AI',
        'content': 'Artificial intelligence is transforming how we work and live. From smart assistants to autonomous vehicles, AI is becoming part of our daily lives.',
    },
    {
        'title': 'Getting Started',
        'content': 'To begin your journey with machine learning, start by understanding the basics of data preparation and model training.',
    },
]

articles.insert(sample_articles)
```

<pre style={{ 'margin': '-20px 20px 0px 20px', 'padding': '0px', 'background-color': 'transparent', 'color': 'black' }}>
  Inserting rows into \`articles\`: 2 rows \[00:00, 423.90 rows/s]
  Inserted 2 rows with 0 errors.
  2 rows inserted, 6 values computed.
</pre>

```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# View articles with generated audio
articles.select(
    articles.title, articles.content, articles.audio
).collect()
```

<div style={{ 'margin': '0px 20px 0px 20px' }} dangerouslySetInnerHTML={{ __html: quartoRawHtml[1] }} />

## Explanation

**OpenAI TTS models:**

<div style={{ 'margin': '0px 20px 0px 20px' }} dangerouslySetInnerHTML={{ __html: quartoRawHtml[2] }} />

**Voice options:**

<div style={{ 'margin': '0px 20px 0px 20px' }} dangerouslySetInnerHTML={{ __html: quartoRawHtml[3] }} />

**Tips:**

* Use `tts-1` for drafts and real-time applications
* Use `tts-1-hd` for final production audio
* Audio is cached—no regeneration on queries

## See also

* [Transcribe
  audio](/howto/cookbooks/audio/audio-transcribe) -
  Convert audio to text
* [Summarize
  podcasts](/howto/cookbooks/audio/audio-summarize-podcast) -
  Transcribe and summarize audio