For AI agents: a documentation index is available at /llms.txt. Markdown versions of all pages can be requested by appending `.md` to the URL, or by setting the `Accept` header to `text/markdown`.
Skip to main content
Deployments

Overview

Learn about the different ways to use our APIs, including cloud services and on-prem containers.

Cloud​

Leverage Speechmatics’ cloud services for easy, scalable, and fully managed speech-to-text and translation capabilities.

The best way to get started using Speechmatics' cloud services is:

On-prem​

Deploy Speechmatics services in your own environment using containers. This option provides maximum control over your deployment and data.

  • CPU speech-to-text container: Deploy the Speechmatics speech-to-text engine as a CPU based containerized service on your own hardware.
  • GPU speech-to-text container: Deploy the Speechmatics speech-to-text engine as a GPU based containerized service on your own hardware.
  • Kubernetes: Deploy the Speechmatics application as a Kubernetes service on your own hardware or your choosen cloud vendor.
  • Language ID container: Identify the language spoken in your audio using the Language ID container.
  • Translation container: Translate audio from one language to another using the Translation container.

Feature availability​

Feature availability varies depending on the deployment method you choose. Below is a table summarizing the speech to text feature availability for each deployment method and processing mode.

Agent STT is available on SaaS only. Where a row lists Agent STT as a mode, the On-prem deployment applies to the Batch and Realtime modes only.

FeatureModesDeployments
Multilingual speech to textBatch, RealtimeSaaS, On-prem
AlignmentBatchSaaS
Audio eventsBatch, RealtimeSaaS, On-prem
Audio filteringBatch, RealtimeSaaS, On-prem
Auto chaptersBatchSaaS
Custom dictionaryBatch, Realtime, Agent STTSaaS, On-prem
DiarizationBatch, Realtime, Agent STT1SaaS, On-prem
Disfluencies and word replacementBatch, Realtime, Agent STTSaaS, On-prem
Feature discoveryBatch, RealtimeSaaS
Fetch URLBatchSaaS, On-Prem
Language identificationBatchSaaS
NotificationsBatchSaaS, On-prem
Punctuation settingsBatch, RealtimeSaaS, On-prem
Sentiment analysisBatchSaaS, On-prem
Smart formattingBatch, RealtimeSaaS, On-prem
Speaker identificationBatch, Realtime, Agent STTSaaS, On-prem2
SummarizationBatchSaaS
Topic detectionBatchSaaS
TrackingBatch, RealtimeSaaS, On-prem
TranslationBatch, RealtimeSaaS, On-prem
Turn detectionRealtimeSaaS, On-prem

Footnotes​

  1. Agent STT supports speaker diarization only, not channel diarization. ↩

  2. On an on-prem deployment, batch speaker identification requires the GPU speech-to-text container. Realtime speaker identification is supported on both CPU and GPU containers. See speaker identification secrets. ↩