> For the complete documentation index, see [llms.txt](https://petes-organization-3.gitbook.io/speechmatics-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://petes-organization-3.gitbook.io/speechmatics-docs/get-started/introduction.md).

# Introduction

## Welcome to Speechmatics

Enterprise-grade APIs for speech-to-text and voice AI agents.

<figure><img src="/files/qrAtPpxS2M989AZa2C7P" alt=""><figcaption></figcaption></figure>

### **What is Speechmatics?**

Speechmatics is a developer platform for integrating speech-to-text and conversational voice AI solutions into your applications and workflows. We handle the underlying voice technology infrastructure, so you can focus on building seamless voice experiences.

With Speechmatics, you can:

* Receive immediate and continuous text transcriptions from live audio streams or calls ([**Real-time**](broken://pages/9nAwyojjPZ6moy38RBsu) transcription)
* Generate complete transcripts from recorded audio files ([**Batch**](broken://pages/87P3XpI5mTtuS84SIFGv) transcription)
* Build voice AI agents that naturally converse with your users ([**Flow**](/speechmatics-docs/voice-agents-flow/overview.md) service).
* Choose flexible deployment options: use our managed SaaS platform or host Speechmatics APIs within your infrastructure ([**on-premises**](/speechmatics-docs/deployments/overview.md))

### Developer quickstart

<table data-column-title-hidden data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Transcribe in real-time</strong></td><td>Instantly convert streaming audio to text with Realtime API</td><td><a href="/pages/ulA90H3jRVLQfESViymn">/pages/ulA90H3jRVLQfESViymn</a></td></tr><tr><td><strong>Transcribe a file</strong></td><td>Use Batch API to accurately turn your audio files into text</td><td><a href="/pages/foTAz7AI9ri2EmIMYHdg">/pages/foTAz7AI9ri2EmIMYHdg</a></td></tr><tr><td><strong>Build a voice agent</strong></td><td>Use our Flow service to build conversational AI agents with ease</td><td><a href="/pages/6Hxb4SQllaeMs6q3rCUd">/pages/6Hxb4SQllaeMs6q3rCUd</a></td></tr></tbody></table>

### Most popular

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>On-premises deployment</strong></td><td>Host our APIs in your environment, ensuring complete data privacy, infrastructure control, and straightforward integration into existing developer workflows and technology stacks.</td><td><a href="/pages/PoXEDSMKoes4vYfZsuYy">/pages/PoXEDSMKoes4vYfZsuYy</a></td></tr><tr><td><strong>On-device deployment [NEW]</strong></td><td>Run our APIs locally, optimizing for low resource usage and data privacy.<br>Ideal for battery-sensitive devices or secure environments, enabling high performance without cloud dependence.</td><td></td></tr><tr><td><strong>API reference</strong></td><td><p>Host our APIs in your environment. </p><p>Ensuring complete data privacy, infrastructure control, and straightforward integration into existing developer workflows and technology stacks.</p></td><td></td></tr><tr><td><strong>Core speech CPU container</strong></td><td>Run our APIs locally, optimizing for low resource usage and data privacy.<br>Ideal for battery-sensitive devices or secure environments, enabling high performance without cloud dependence.</td><td><a href="/pages/m0ktCVbeCxByDAVBZ3K7">/pages/m0ktCVbeCxByDAVBZ3K7</a></td></tr></tbody></table>

## Start building

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><strong>Radio station translator</strong></td><td>Use Real-time API to build a live radio stream translator </td></tr><tr><td><strong>Voice agent app</strong></td><td>Create a conversational AI app with React Native and Flow</td></tr><tr><td><strong>Voice agent web app</strong></td><td>Build it with Next.js and Flow</td></tr><tr><td><strong>Microphone setup for transcription</strong></td><td>Read tips on using FFMPEG</td></tr></tbody></table>

## &#x20;

<table data-view="cards" data-full-width="false"><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><strong>Help center</strong></td><td>Explore FAQs</td></tr><tr><td><strong>GitHub</strong></td><td>Access GitHub </td></tr><tr><td>Status</td><td>Check the status of our services</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://petes-organization-3.gitbook.io/speechmatics-docs/get-started/introduction.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.