# Speech to Text overview

Learn how to turn audio into text.

Use Speech to Text to transcribe using one of the modes:

* [Realtime processing](#realtime-processing): Stream audio from an input device or file and receive instant updates of the transcription as it happens
* [Batch processing](#batch-processing): Submit an audio file and receive a complete text transcription once the processing is finished
* [Agent STT](#agent-stt): Stream audio from a conversation and receive speaker-labelled, turn-based transcription for a voice agent

## 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)

[Submit an audio file and receive a complete text transcription once the processing is finished](/speech-to-text/batch/quickstart.md)

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

[Stream audio and receive speaker-labelled, turn-based transcription ready to pass to an LLM](/speech-to-text/agent-stt/quickstart.md)

The quickest way to transcribe voice from audio is in our [web portal](https://portal.speechmatics.com/jobs/create/batch).

## Deployments[​](#deployments "Direct link to Deployments")

Speechmatics provides flexible deployment options tailored to your requirements. You can host the platform in your own environment, use our managed service, or choose a hybrid approach.

For deploying our API in your environment, [contact sales](https://www.speechmatics.com/speak-to-sales), or see our [on-prem documentation](/deployments/.md).

## Realtime processing[​](#realtime-processing "Direct link to Realtime processing")

Turn live audio into accurate transcripts — instantly.

The [Speechmatics Realtime Speech to Text API](/api-ref/realtime-transcription-websocket.md) converts spoken audio into text with low latency and high accuracy.

* Use when speed matters
* Transcribe live broadcasts or events
* Caption webinars, meetings, or podcasts in real time
* Power voice assistants or AI agents with live input
* Monitor contact center calls as they happen
* Build accessibility features like live captions

## Batch processing[​](#batch-processing "Direct link to Batch processing")

Create transcripts from pre-recorded audio or video.

The [Speechmatics Batch Speech to Text API](/api-ref/batch/create-a-new-job.md) processes pre-recorded files asynchronously by default, returning highly accurate transcripts in a range of formats. To block for the result in a single request instead, use [synchronous transcription](/speech-to-text/batch/synchronous.md).

* Transcribe recorded meetings or interviews
* Caption on-demand videos and podcasts
* Generate searchable transcripts for media archives
* Process customer service recordings for compliance or insights
* Automate subtitles across large video libraries

### What is a job?[​](#what-is-a-job "Direct link to What is a job?")

Each transcription request is handled as a job — a self-contained unit representing a single transcription task.

A job includes:

* The audio or video file to be transcribed
* Configuration settings (e.g. language, formatting, diarization)
* Metadata and status tracking
* The resulting transcript(s)

You submit a job to the API, monitor its progress, and retrieve results once it's complete. Jobs can be created via direct upload or by referencing a URL.

## Agent STT[​](#agent-stt "Direct link to Agent STT")

Transcription built for voice agents and conversational applications.

[Agent STT](/speech-to-text/agent-stt/.md) groups the transcript into [segments](/speech-to-text/agent-stt/segmentation.md): punctuated, attributed to a speaker, and ready to pass to an LLM. It also marks where each speaker's [turn](/speech-to-text/agent-stt/turn-detection.md) starts and ends, so your agent knows when to respond.

* Build a voice agent or live conversational assistant
* Respond as soon as a caller stops speaking
* Feed clean, speaker-labelled turns to an LLM
* Handle multi-speaker calls without stitching words together

## Quicklinks[​](#quicklinks "Direct link to Quicklinks")

#### [Languages](/speech-to-text/languages.md)

[See the languages Speechmatics supports](/speech-to-text/languages.md)

#### [Pricing](https://www.speechmatics.com/pricing)

[Compare our pricing options](https://www.speechmatics.com/pricing)

#### [Translation](/speech-to-text/features/translation.md)

[Translate your transcript to another language](/speech-to-text/features/translation.md)

#### [Custom dictionary](/speech-to-text/features/custom-dictionary.md)

[Add custom words to your transcript](/speech-to-text/features/custom-dictionary.md)

#### [Diarization](/speech-to-text/features/diarization.md)

[Identify speakers in your transcript](/speech-to-text/features/diarization.md)

#### [Accuracy benchmarking](/speech-to-text/accuracy-benchmarking.md)

[Benchmark the accuracy of our models](/speech-to-text/accuracy-benchmarking.md)
