Last updated 10/20/2021

Deepgram provides a variety of tools to help you label, train, process, and manage the audio transcription process.


Use our RESTful APIs to easily enable additional transcription and understand features like punctuation, speaker diarization, and redaction. No need to create different jobs for different file extensions.

Speech Recognition

Deepgram's Speech Recognition API gives you streamlined access to automatic transcription from Deepgram's off-the-shelf and trained speech recognition models. This product is very fast, can understand nearly every audio format available, and is customizable. You can customize your transcript using various query parameters and apply general purpose and custom-trained AI models. To learn more, see Speech Recognition API Reference.


Deepgram’s Mission Control API provides programmatic access to many of the features found in Deepgram’s console. Its endpoints allow you to prepare training data, train and deploy custom speech models, and manage your account. To learn more, see MissionControl API Reference.

Data labeling

The more labeled data you have, the more gains you can see in accuracy over time. As a Deepgram hosted customer, you can upload pre-labeled files or have Deepgram expertly label data for you. Alternatively, if you want to keep your data on premise, we will provide you with state-of-the-art labeling tools.


UniMRCP Plugin

Server plugin for UniMRCP that allows Deepgram Speech Recognition to be used as a speech recognizer resource (speechrecog) in an MRCP server. To see the code, visit the UniMRCP Plugin Github repository.