Deepgram Changelog

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

New Method for Closing Streams

Deepgram’s real-time API has been updated for enhanced usability. Streaming connections should now be closed by sending the JSON message { "type": "CloseStream" } . Previously, streaming connections were closed by sending an empty byte….

New Enhanced German Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include German to bring you the highest accuracy for German language support. For example, to call the Enhanced German Model,…

New Enhanced Polish Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Polish to bring you the highest accuracy for Polish language support. For example, to call the Enhanced Polish Model,…

New Enhanced Japanese Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Japanese to bring you the highest accuracy for Japanese language support. For example, to call the Enhanced Japanese Model,…

New Enhanced Korean Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Korean to bring you the highest accuracy for Korean language support. For example, to call the Enhanced Korean Model,…

New Enhanced Italian Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Italian to bring you the highest accuracy for Italian language support. For example, to call the Enhanced Italian Model,…

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…

New Enhanced Portuguese Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Portuguese (Brazil and Portugal) to bring you the highest accuracy for Portuguese language support. For example, to call the…

New Base Polish Model

Deepgram is excited to announce our new Base Polish model. To call the Base Polish model, the URL query might look like: https://api.deepgram.com/v1/listen?model=general&tier=base&language=pl&punctuate=true To learn more about the various parameters you can use to customize…

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 Enhanced Dutch Model

Deepgram is excited to announce expanding our newest, most powerful ASR model tier, Enhanced, to include Dutch to bring you the highest accuracy for Dutch language support. For example, to call the General Enhanced Dutch…

Deepgram On-Premises Release 220831

Deepgram released a new version of its on-premises solution. On-Premises Release 220831 Docker Hub Images deepgram/onprem-api:1.64.0 deepgram/onprem-engine:3.33.0 deepgram/onprem-license-proxy:1.2.1 deepgram/onprem-billing:1.4.0 deepgram/onprem-metrics-server:2.0.0 This Release Contains The Following Changes Support for improved Diarization. The new Diarization model should…

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…