Deepgram Changelog

Stay up to date with enhancements to our AI Speech Platform and ecosystem

Deepgram On-Premises Release 221031

Deepgram released a new version of its on-premises solution. On-Premises Release 221031: Docker Hub Images deepgram/onprem-api:1.72.2 deepgram/onprem-engine:3.37.8 deepgram/onprem-license-proxy:1.2.2 deepgram/onprem-billing:1.4.0 deepgram/onprem-metrics-server:2.0.0 Changes Deepgram On-premises users can now choose between Deepgram’s Base and Enhanced models in an…

Deepgram On-Premises Release 221007

Deepgram released a new version of its on-premises solution. On-Premises Release 221007: Docker Hub Images deepgram/onprem-api:1.70.0 deepgram/onprem-engine:3.37.2 deepgram/onprem-license-proxy:1.2.1 deepgram/onprem-billing:1.4.0 deepgram/onprem-metrics-server:2.0.0 Changes Deepgram On-premises deployments now support the following Understanding features (with the accompanying Understanding model…

Introducing Language Detection

Today, we’re very excited to announce the public release of our new Automatic Language Detection feature(detect_language=true), which supports all of our generally available languages.  Deepgram’s speech recognition API, with Language Detection, can automatically detect the dominant…

Introducing Topic Detection

We are very excited to announce our latest Speech Understanding feature – Topic Detection (detect_topics=true). Deepgram’s Topic Detection API, in addition to our speech-to-text API, uses deep learning techniques to generate, identify and extract key…

Introducing Summarization

We are excited to announce our latest Speech Understanding feature – Summarization (summarize=true). Deepgram’s speech recognition API, with Summarization, can auto-generate meaningful summaries from the audio data. Summarization API endpoint can be called using (summarize=true)…

New Paragraph and Sentence Formatting

paragraphs=true&punctuate=true (required — When paragraphs=true, punctuation, diarization, and/or multichannel must be enabled) Our new paragraphs feature breaks audio transcripts into nicely-formatted paragraphs and sentences for easier reading and parsing. The feature can be influenced by the…

Announcing new ‘tier’ parameter

Deepgram is continuing to expand our selection of Enhanced Models to bring you the highest accuracy across many languages and use-cases.  To better support these models, we have deployed a new `tier` parameter to be…

Now in General Availability: Utterance Formatting

utterances=true (optional parameter utt_split=number) Our new utterances feature segments speech into meaningful semantic units, which allows the chosen model to interact more naturally and effectively with speakers’ spontaneous speech patterns. For example, when humans speak…

Open Beta: Redaction – Support for Social Security Numbers

redact=ssn We’ve added beta support for redaction of social security numbers from automatic transcripts. To test the feature, send your audio to beta.deepgram.com and set redact to true. To learn more about the feature and participate…

Open Beta: Utterance Formatting

utterances=true Our new utterances feature segments speech into meaningful semantic units, which allows the chosen model to interact more naturally and effectively with speakers’ spontaneous speech patterns. For example, when humans speak to each other…

Keyword Boosting Effect

On February 17, we released our improved keyword boosting feature which can be used to boost or suppress recognition of certain keywords. We have determined that some words that are unfamiliar to the speech model…

Improved Keyword Boosting

keywords={keyword} We are releasing an updated keyword boosting feature (keywords={keyword}) with improved support for out of vocabulary words. Keywords can be boosted or suppressed with this feature.  Note, that this is not a persistent feature…

Improved Punctuation

punctuate=true We’ve recently adopted a new approach for how our ASR models predict punctuated outputs. Previously, this was handled as part of a post-processing step. Now, utilizing our newly developed and novel model architecture, we…