Deepgram Changelog

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 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…

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…

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…

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)…

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…

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…

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…

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…

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…

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…

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…

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…