# Welcome to Speechmatics

Everything you need to integrate Speechmatics, from your first API call to production.

Speechmatics provides enterprise-grade APIs for Speech to Text, Text to Speech, and building voice agents.

Pick a starting point below.

## Developer quickstart[​](#developer-quickstart "Direct link to Developer quickstart")

#### [Transcribe in real time](/speech-to-text/realtime/quickstart.md)

[Instantly convert streaming audio to text with Realtime processing](/speech-to-text/realtime/quickstart.md)

#### [Transcribe a file](/speech-to-text/batch/quickstart.md)

[Use Batch processing to accurately turn your audio files into text](/speech-to-text/batch/quickstart.md)

#### [Transcribe for a voice agent](/speech-to-text/agent-stt/quickstart.md)

[Use Agent STT to get turn-based transcription ready to pass to an LLM](/speech-to-text/agent-stt/quickstart.md)

#### [Generate speech from text](/text-to-speech/quickstart.md)

[Use our Text to Speech API to generate speech from text](/text-to-speech/quickstart.md)

## Build with Speechmatics[​](#build-with-speechmatics "Direct link to Build with Speechmatics")

#### [Build a voice agent](/speech-to-text/agent-stt/.md)

[Use our integrations to build voice agents with ease](/speech-to-text/agent-stt/.md)

#### [Use our SDKs](/integrations-and-sdks/sdks.md)

[Integrate Speechmatics quickly with SDKs for your language](/integrations-and-sdks/sdks.md)

## Deployment options[​](#deployment-options "Direct link to Deployment options")

#### [Cloud SaaS](/deployments/.md#cloud)

[Access Speechmatics APIs as a fully managed cloud service. No infrastructure to deploy or maintain — just send audio and receive transcripts. Ideal for fast time-to-value, dynamic scaling, and teams that want to focus on building rather than operations.](/deployments/.md#cloud)

#### [On-prem deployment](/deployments/.md#on-prem)

[Host our APIs in your environment, ensuring complete data privacy, infrastructure control, and straightforward integration into existing developer workflows and technology stacks](/deployments/.md#on-prem)

#### [GPU container](/deployments/container/gpu-speech-to-text.md)

[Run our APIs on GPU-accelerated infrastructure for maximum throughput and lowest latency. Best suited to high-volume workloads and real-time applications where processing speed is the priority.](/deployments/container/gpu-speech-to-text.md)

#### [Kubernetes](/deployments/kubernetes/.md)

[Deploy our APIs across Kubernetes clusters for elastic scaling, automated orchestration, and resilient operations. A natural fit for teams with existing K8s infrastructure who need production-grade speech processing at scale.](/deployments/kubernetes/.md)

## Tools and reference[​](#tools-and-reference "Direct link to Tools and reference")

#### [Visit the portal](https://portal.speechmatics.com)

[Create API keys, manage billing, explore transcription tools, and build voice AI agents in our web platform.](https://portal.speechmatics.com)

#### [API reference](/api-ref/.md)

[Explore our API reference. Available for: Realtime transcription, Batch transcription and Agent STT.](/api-ref/.md)