Releasesby GlyphFIPS 140-3 Images (General Availability)
FIPS 140-3 images are now generally available for all four self-hosted services, published under the -fips tag suffix: quay.io/deepgram/self-hosted-api:release-260728-fips quay.io/deepgram/self-hosted-engine:release-260728-fips quay.io/deepgram/self-hosted-license-proxy:release-260728-fips quay.io/deepgram/self-hosted-billing:release-260728-fips These...
Also shipped Jul 28, 2026Deepgram in July 2026 →
AI code suggestions in Workspaces (General availability)
AI code suggestions in Cortex Code are now generally available. This release also includes updated keybindings and bug fixes. Notebook Python cells , no changes to keybindings.
Snowflake Native Apps support for Virtual Private Snowflake on AWS for apps with containers (General availability)
Snowflake Native App with Snowpark Container Services now support Virtual Private Snowflake (VPS) on Amazon Web Services. Apps with containers can be distributed to Snowflake customers in VPS deployments. Apps running in VPS can use the functionality of Snowpark Container Services, including compute pools, services, jobs, and external access integrations.
Python UDTFs in Unity Catalog are now generally available
Registering Python user-defined table functions (UDTFs) in Unity Catalog is now generally available in Databricks Runtime 18. A Unity Catalog Python UDTF is a governed function that returns a table, invoked in the FROM clause of a SQL statement to return multiple rows and columns.
Note: IAM group authentication is available in Preview for new AlloyDB clusters
Note: IAM group authentication is available in Preview for new AlloyDB clusters. To enable this feature on an existing cluster, contact your Google Cloud account team. IAM group authentication for AlloyDB is available in Preview for new clusters running PostgreSQL 15 and later.
Vercel Connect now supports Custom Environments
Vercel Connect now lets you link a connector to a Custom Environment so deployments there can request provider tokens and receive forwarded webhooks. Custom Environments appear alongside Production, Preview, and Development when you add or edit a project on a connector in the dashboard.
AIP Document Intelligence: deploy extraction strategies as Python functions (GA)
Deploying extraction strategies to Python functions is generally available in AIP Document Intelligence, as an alternative to running a strategy in a batch pipeline.
More from DeepgramEvery Deepgram release →
Container Images (release 260728)
- quay.io/deepgram/self-hosted-api:release-260728 Equivalent image to: quay.io/deepgram/self-hosted-api:1.192.12-1 quay.io/deepgram/self-hosted-engine:release-260728 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.123.0-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260728 Equivalent...
This Release Contains The Following Changes
- Formatting Improvements , added Korean numeral support and fractional number formatting; decimal values now preserve their trailing zeros; and Japanese spacing has been improved. New .dgv2 Model File Format , release-260728 images (both standard and FIPS) support the new .dgv2 encrypted model file format. FIPS container images can only load .dgv2 models.
UpdateListen: switch model and language mid-session
UpdateListen now accepts model and language changes, so you can switch speech-to-text models and languages without restarting the session. Previously the provider identity had to match the current session.
STT latency in LatencyReport
LatencyReport now includes stt_latency , the time from audio received to transcript produced. Every turn reports the full STT → LLM → TTS breakdown. { "type": "LatencyReport", "stt_latency": 0.12, "ttt_token_latency": 0.34, "tts_latency": 0.18, "total_latency": 0.64 } For details, see the Latency Report documentation .
Maximum session length of 2 hours
Voice Agent sessions now close automatically after 2 hours. Two new codes mark the limit: Time into the session Event Code 1 hour 55 minutes Warning MAXIMUM_SESSION_LENGTH_APPROACHING 2 hours Error (terminal) MAXIMUM_SESSION_LENGTH_REACHED KeepAlive does not extend the limit.
Google Enterprise Agent API support
Managed Google LLMs now run on either of Google's APIs: the AI Studio API or the Gemini Enterprise Agent (GEA) API, formerly the Vertex API. GEA adds regional Google endpoints for models where available. Select the API with think.provider.version from any Deepgram Voice Agent endpoint: ai-studio-v1beta for AI Studio, gemini-enterprise-agent-v1 for GEA.
Fixed
Resolved a sample rate issue that prevented some users from using the Flux TTS early access model in the Voice Agent.
SDK support for Flux numerals
The Flux numerals feature is now available in the JavaScript, Python, and Java SDKs. Set numerals=true when you open a Flux WebSocket connection to convert spoken numbers into their numerical format (for example, "nine hundred" becomes "900"). On Flux, numerals is set at connection time only and cannot be changed through the Configure message.