Releasesby GlyphContainer Images (release 260528)
- quay.io/deepgram/self-hosted-api:release-260528 Equivalent image to: quay.io/deepgram/self-hosted-api:1.188.1 quay.io/deepgram/self-hosted-engine:release-260528 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.117.0 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260528 Equivalent image to...
Also shipped May 28, 2026Deepgram in May 2026 →
Hex now connects to your apps as an MCP client
🔌 Hex is now an MCP client Your data tells you what happened. The why lives somewhere else , in strategy docs, meeting notes, Slack threads, customer conversations. Today, the Hex agent can read all of it. Connect any tool that exposes an MCP server to the Hex agent. As part of our public beta, we’re launching with two named connectors: Notion & Linear.
Pipelines pricing announced
Cloudflare Pipelines is a streaming data platform that ingests events, transforms them with SQL, and writes to R2 as JSON, Parquet, or Apache Iceberg ↗ tables. Pipelines now has published pricing based on two usage dimensions: the volume of data processed by SQL transforms and the volume of data delivered to sinks. Ingress into a Pipeline stream is free.
R2, R2 Data Catalog - R2 Data Catalog pricing announced
R2 Data Catalog is a managed Apache Iceberg ↗ data catalog built directly into R2 buckets, queryable by any Iceberg-compatible engine such as Spark, Snowflake, and DuckDB. R2 Data Catalog now has published pricing for catalog operations and table compaction, in addition to standard R2 storage and operations . Billing is not yet enabled.
R2 SQL pricing announced
R2 SQL is a serverless, distributed query engine that runs SQL against Apache Iceberg ↗ tables stored in R2 Data Catalog . R2 SQL now has published pricing based on a single dimension: the volume of compressed data scanned to execute your queries.
You can now use the DigitalOcean Control Panel to create, connect to, tag, resize, and restore Managed...
You can now use the DigitalOcean Control Panel to create, connect to, tag, resize, and restore Managed Weaviate clusters (in private preview). See the Managed Weaviate docs for more information.
Linear Diffs
Agents generate large volumes of code, but individuals are still accountable for the changes that merge. This leads to a lot of review work, and the capability and performance of traditional review tools hasn't kept up. Today, we're releasing Linear Diffs to make reviewing code a fast and fluid experience native to Linear.
More from DeepgramEvery Deepgram release →
Preparation for a future Engine container change
The official Helm chart ( 0.37.0 and later) and the Docker and Podman compose files in deepgram/self-hosted-resources now set NVIDIA_VISIBLE_DEVICES=all and NVIDIA_DRIVER_CAPABILITIES=compute,utility on the Engine container.
This Release Contains The Following Changes
- Profanity Filtering for STT Multilingual , profanity_filter=true now masks recognized profanity in STT multilingual transcripts ( language=multi ). See Profanity Filtering for the supported language list and usage.
🆕 Improved Nova-3 Medical Batch Model Released
We’ve released an upgraded Nova-3 Medical batch model with improved medical term recognition. Key Improvements: Expands the model’s medical vocabulary with new medical terms Boosts medical term recognition to 97.20% KRR Maintains WER parity with no observed regression on common or conversational terms
Gemini 3.5 Flash Now Available
gemini-3.5-flash is now available as a managed Google LLM in the Voice Agent API. This Standard tier model brings improved performance and efficiency to your voice agents. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.5-flash", "temperature": 0.5 } } } }
Deprecation Notice
The Gemini 2.5 Flash family of models is deprecating in October. Start testing newer models now to ensure a smooth migration. For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .
🆕 Profanity Filtering for Multilingual Models
Deepgram’s Profanity Filtering feature is now available for all multilingual models: Nova-2 multilingual , Nova-3 multilingual , and Flux multilingual ( language=multi ). You can enable profanity filtering in your API requests by setting the profanity_filter=true parameter.
🛠️ Fix: Improved Word Spacing in Korean Transcripts
We fixed an issue affecting Korean transcripts ( ko , ko-KR ) where word spacing was sometimes missing. Transcripts should now better reflect proper Korean spacing, improving readability for users working with Korean audio. See the full list of supported languages on the Models & Languages Overview page .
Gemini 3.1 Flash Lite Now Available
gemini-3.1-flash-lite is now available as a managed Google LLM in the Voice Agent API. This Standard tier model replaces the preview version. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.1-flash-lite", "temperature": 0.5 } } } }