Releasesby GlyphCorrection: Browser Agent SDK has no client-side VAD
The Browser Agent SDK never shipped client-side Silero voice activity detection. Documentation published with the SDK described it as an available feature, and that documentation was wrong. The following did not exist in any released package: The vad option on MicrophoneOptions in @deepgram/agents . The speechThreshold and silenceThreshold VAD options.
Also shipped Sep 18, 2026Deepgram in September 2026 →
Databricks Apps telemetry is now generally available
Configuring telemetry for your Databricks apps is now generally available. Databricks Apps telemetry collects traces, logs, and metrics and persists them to Unity Catalog tables using the OpenTelemetry (OTel) protocol.
Lakebase Search is generally available
Lakebase Search is now generally available. It brings scalable vector and keyword search to Lakebase projects through two Postgres extensions, so you can run semantic and exact-term search in a single database without a separate search stack: lakebase_vector adds the lakebase_ann index type for approximate nearest-neighbor vector search.
Apache Iceberg™ tables: Partition evolution (General availability)
With this release, we're pleased to announce the general availability of partition evolution for Snowflake-managed Iceberg tables. You can now change a table's partition specification after you create the table by adding, dropping, or replacing partition fields, without rewriting existing data.
xAI's Grok 4.6 is generally available
Grok 4.6 is now generally available (GA) and available for production use on the global endpoint and the US multi-region endpoint.
Gemini Enterprise: Support for new actions (Public Preview)
Support for new actions is available in Public Preview for the following data stores: Microsoft OneDrive : Copy folder, move file, move folder, rename file, rename folder, share file or folder, and update file properties. Microsoft Outlook : Create calendar, RSVP to event, and update calendar.
Agent Platform SDK for Python version 2.0.1 is available
Version 2.0.1 of the Agent Platform SDK for Python ( google-cloud-agentplatform ) is now available. This release migrates generative AI modules to the Google Gen AI SDK, decouples the agent surface from google-cloud-aiplatform into a dedicated package, and introduces restructured namespaces.
More from DeepgramEvery Deepgram release →
Correction: token minting uses ttl_seconds
The server-side token-minting example on the Browser Agent SDK overview posted {"ttl": 30} to POST /v1/auth/grant . The field is named ttl_seconds : body: JSON.stringify({ ttl_seconds: 30 }), /v1/auth/grant accepts unrecognized fields, returns 200 , and issues a token with the 30-second default, so a request built from the old example raised no error while...
Nova-3 Pharma: Speech-to-Text for Pharmaceutical Use Cases (English)
We have released nova-3-pharma , a new Nova-3 model purpose-built for pharmaceutical vocabulary, with a focus on accurate drug-name recognition. It is designed for pharmacy and healthcare voice-agent workflows where getting the medication right matters most. Available in English for both batch and streaming.
Container Images (release 260915)
- quay.io/deepgram/self-hosted-api:release-260915 Equivalent image to: quay.io/deepgram/self-hosted-api:1.192.37 quay.io/deepgram/self-hosted-engine:release-260915 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.131.2 Minimum required NVIDIA driver version: >=580 , open kernel module flavor The minimum driver version has increased this release ...
FIPS 140-3 Images
FIPS 140-3 images are available for all four self-hosted services, published under the -fips tag suffix: quay.io/deepgram/self-hosted-api:release-260915-fips Equivalent image to: quay.io/deepgram/self-hosted-api:1.192.37-fips quay.io/deepgram/self-hosted-engine:release-260915-fips Equivalent image to: quay.io/deepgram/self-hosted-engine:3.131.2-fips...
This Release Contains The Following Changes
- NVIDIA Blackwell GPU Support (GA) , Blackwell-generation GPUs are now generally available for self-hosted deployments. See Drivers and Containerization Platforms for driver requirements and Model and GPU Compatibility for which models run on which GPUs.
Nova-3 Improved Models for Danish, Estonian, Flemish, Italian, Lithuanian, Macedonian, Polish, Urdu, and Vietnamese
We have released improved Nova-3 monolingual models for nine existing languages. These updates enhance transcription quality for batch and streaming workloads.
Improved models
Batch and streaming models Polish ( pl ) Danish ( da ) Batch models Vietnamese ( vi ) Flemish ( nl-BE ) Streaming models Estonian ( et ) Macedonian ( mk ) Urdu ( ur ) Italian ( it ) Lithuanian ( lt ) You do not need to change your API requests to access the improvements to existing languages; the updates are live for all users.
SDK releases
Deepgram Python SDK v7.9.0 , JavaScript SDK v5.11.0 , and Java SDK v0.10.0 are now available. All three releases add Voice Agent ForceEndTurn support, Flux TTS expressivity controls for Agent providers, and the expanded Flux TTS speed range of 0.5 through 1.5 in 0.05 increments.